< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 894 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: 2.4323. Min Range: -2.4323

Max Act: 2.4323. Min Act: -0.1700

Data Index: 6389651 (Open Web Text)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.4154. Min Act: -0.1700

Data Index: 4226232 (Open Web Text)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.3538. Min Act: -0.1700

Data Index: 3869260 (Open Web Text)

Max Activating Token Index: 816

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.3426. Min Act: -0.1700

Data Index: 6173643 (Open Web Text)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.3366. Min Act: -0.1700

Data Index: 2992740 (Open Web Text)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.3172. Min Act: -0.1700

Data Index: 8819998 (Open Web Text)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.3070. Min Act: -0.1700

Data Index: 1658935 (Open Web Text)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.3113. Min Act: -0.1700

Data Index: 1643213 (Open Web Text)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2999. Min Act: -0.1700

Data Index: 8075908 (Open Web Text)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.3059. Min Act: -0.1700

Data Index: 8224668 (Open Web Text)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2849. Min Act: -0.1700

Data Index: 4185478 (Open Web Text)

Max Activating Token Index: 141

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2822. Min Act: -0.1700

Data Index: 5219559 (Open Web Text)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2803. Min Act: -0.1700

Data Index: 4879752 (Open Web Text)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2783. Min Act: -0.1700

Data Index: 5399640 (Open Web Text)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2625. Min Act: -0.1700

Data Index: 7570202 (Open Web Text)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2670. Min Act: -0.1700

Data Index: 5333207 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2635. Min Act: -0.1700

Data Index: 6139362 (Open Web Text)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2526. Min Act: -0.1700

Data Index: 3048366 (Open Web Text)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2535. Min Act: -0.1700

Data Index: 581648 (Open Web Text)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4323. Min Range: -2.4323

Max Act: 2.2556. Min Act: -0.1700

Data Index: 7801568 (Open Web Text)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #19