< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 806 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: 2.6852. Min Range: -2.6852

Max Act: 2.6852. Min Act: -0.1700

Data Index: 8538661 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.6424. Min Act: -0.1700

Data Index: 8538675 (Open Web Text)

Max Activating Token Index: 181

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5973. Min Act: -0.1700

Data Index: 155853 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5411. Min Act: -0.1700

Data Index: 4891330 (Open Web Text)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5707. Min Act: -0.1700

Data Index: 4552046 (Open Web Text)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5575. Min Act: -0.1700

Data Index: 13148 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5468. Min Act: -0.1700

Data Index: 5133385 (Open Web Text)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5616. Min Act: -0.1700

Data Index: 2181697 (Open Web Text)

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5561. Min Act: -0.1700

Data Index: 588965 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5456. Min Act: -0.1700

Data Index: 8538658 (Open Web Text)

Max Activating Token Index: 728

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5446. Min Act: -0.1700

Data Index: 3290059 (Open Web Text)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5354. Min Act: -0.1700

Data Index: 662270 (Open Web Text)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5267. Min Act: -0.1700

Data Index: 472783 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5344. Min Act: -0.1700

Data Index: 6816917 (Open Web Text)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5459. Min Act: -0.1700

Data Index: 3325510 (Open Web Text)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.4941. Min Act: -0.1700

Data Index: 1187902 (Open Web Text)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.4942. Min Act: -0.1700

Data Index: 2128101 (Open Web Text)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5204. Min Act: -0.1700

Data Index: 8538664 (Open Web Text)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5151. Min Act: -0.1700

Data Index: 5216312 (Open Web Text)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6852. Min Range: -2.6852

Max Act: 2.5176. Min Act: -0.1700

Data Index: 8024876 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #19