< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 473 in Layer 2

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: 2.1426. Min Range: -2.1426

Max Act: 2.1426. Min Act: -0.1700

Data Index: 3155134 (Open Web Text)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0965. Min Act: -0.1700

Data Index: 8288048 (Open Web Text)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0689. Min Act: -0.1700

Data Index: 661119 (Open Web Text)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.1045. Min Act: -0.1700

Data Index: 3851047 (Open Web Text)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0531. Min Act: -0.1700

Data Index: 4882737 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0637. Min Act: -0.1700

Data Index: 2085184 (Open Web Text)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0676. Min Act: -0.1700

Data Index: 1956068 (Open Web Text)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0418. Min Act: -0.1700

Data Index: 1761281 (Open Web Text)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.1426. Min Range: -2.1426

Max Act: 1.9968. Min Act: -0.1700

Data Index: 8432020 (Open Web Text)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0250. Min Act: -0.1700

Data Index: 434539 (Open Web Text)

Max Activating Token Index: 42

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0344. Min Act: -0.1700

Data Index: 2412598 (Open Web Text)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0584. Min Act: -0.1700

Data Index: 6424612 (Open Web Text)

Max Activating Token Index: 694

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0248. Min Act: -0.1700

Data Index: 1172900 (Open Web Text)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0350. Min Act: -0.1700

Data Index: 7130531 (Open Web Text)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0028. Min Act: -0.1700

Data Index: 4539281 (Open Web Text)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0201. Min Act: -0.1700

Data Index: 8820271 (Open Web Text)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0272. Min Act: -0.1700

Data Index: 4401543 (Open Web Text)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.1426. Min Range: -2.1426

Max Act: 1.9758. Min Act: -0.1700

Data Index: 8044296 (Open Web Text)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0104. Min Act: -0.1700

Data Index: 3590227 (Open Web Text)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.1426. Min Range: -2.1426

Max Act: 2.0006. Min Act: -0.1700

Data Index: 4966369 (Open Web Text)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #19