< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 325 in Layer 5

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: 2.5463. Min Range: -2.5463

Max Act: 2.5463. Min Act: -0.1700

Data Index: 8061186 (Open Web Text)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.4268. Min Act: -0.1700

Data Index: 2365208 (Open Web Text)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3948. Min Act: -0.1700

Data Index: 7660573 (Open Web Text)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3970. Min Act: -0.1700

Data Index: 7507318 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.4015. Min Act: -0.1700

Data Index: 8506846 (Open Web Text)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3738. Min Act: -0.1700

Data Index: 2602507 (Open Web Text)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3822. Min Act: -0.1700

Data Index: 5584585 (Open Web Text)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3672. Min Act: -0.1700

Data Index: 6947784 (Open Web Text)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3555. Min Act: -0.1700

Data Index: 2255446 (Open Web Text)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3669. Min Act: -0.1700

Data Index: 2877234 (Open Web Text)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3566. Min Act: -0.1700

Data Index: 162779 (Open Web Text)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3675. Min Act: -0.1700

Data Index: 437098 (Open Web Text)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3766. Min Act: -0.1700

Data Index: 2249095 (Open Web Text)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3415. Min Act: -0.1700

Data Index: 5364526 (Open Web Text)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3365. Min Act: -0.1700

Data Index: 175725 (Open Web Text)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3596. Min Act: -0.1700

Data Index: 4564974 (Open Web Text)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3359. Min Act: -0.1700

Data Index: 8032919 (Open Web Text)

Max Activating Token Index: 133

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3223. Min Act: -0.1700

Data Index: 3927520 (Open Web Text)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3295. Min Act: -0.1700

Data Index: 2474248 (Open Web Text)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.5463. Min Range: -2.5463

Max Act: 2.3231. Min Act: -0.1700

Data Index: 16038 (Open Web Text)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #19