< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1301 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.3970. Min Act: -0.1700

Data Index: 6944657 (Open Web Text)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.4017. Min Act: -0.1700

Data Index: 8614056 (Open Web Text)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.2503. Min Act: -0.1700

Data Index: 1094110 (Open Web Text)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.0921. Min Act: -0.1700

Data Index: 3546000 (Open Web Text)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.0921. Min Act: -0.1700

Data Index: 3002449 (Open Web Text)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.0081. Min Act: -0.1700

Data Index: 410548 (Open Web Text)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.0269. Min Act: -0.1700

Data Index: 4007749 (Open Web Text)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.9890. Min Act: -0.1700

Data Index: 6285424 (Open Web Text)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.0225. Min Act: -0.1700

Data Index: 3671088 (Open Web Text)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.9456. Min Act: -0.1700

Data Index: 5068181 (Open Web Text)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.0457. Min Act: -0.1700

Data Index: 6768691 (Open Web Text)

Max Activating Token Index: 395

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.9206. Min Act: -0.1700

Data Index: 5237386 (Open Web Text)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 10.4017. Min Range: -10.4017

Max Act: 10.0798. Min Act: -0.1700

Data Index: 8059543 (Open Web Text)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.7697. Min Act: -0.1700

Data Index: 8041532 (Open Web Text)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.9408. Min Act: -0.1700

Data Index: 2512748 (Open Web Text)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.9051. Min Act: -0.1700

Data Index: 3937298 (Open Web Text)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.8718. Min Act: -0.1700

Data Index: 8199385 (Open Web Text)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.9021. Min Act: -0.1700

Data Index: 4729538 (Open Web Text)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.8295. Min Act: -0.1700

Data Index: 2637682 (Open Web Text)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 10.4017. Min Range: -10.4017

Max Act: 9.7980. Min Act: -0.1700

Data Index: 3179966 (Open Web Text)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #19