< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2640 in Layer 4

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: 2.5761. Min Range: -2.5761

Max Act: 2.5761. Min Act: -0.1700

Data Index: 3433947 (Open Web Text)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.5287. Min Act: -0.1700

Data Index: 1325420 (Open Web Text)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.4309. Min Act: -0.1700

Data Index: 6929697 (Open Web Text)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.4205. Min Act: -0.1700

Data Index: 7691782 (Open Web Text)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.4285. Min Act: -0.1700

Data Index: 98600 (Open Web Text)

Max Activating Token Index: 556

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.4386. Min Act: -0.1700

Data Index: 2705725 (Open Web Text)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.4295. Min Act: -0.1700

Data Index: 8123966 (Open Web Text)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.4258. Min Act: -0.1700

Data Index: 292116 (Open Web Text)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.3963. Min Act: -0.1700

Data Index: 3868455 (Open Web Text)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.4016. Min Act: -0.1700

Data Index: 7604282 (Open Web Text)

Max Activating Token Index: 695

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.4007. Min Act: -0.1700

Data Index: 4792185 (Open Web Text)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.4159. Min Act: -0.1700

Data Index: 7937274 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.3698. Min Act: -0.1700

Data Index: 8149145 (Open Web Text)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.3889. Min Act: -0.1700

Data Index: 1687324 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.3924. Min Act: -0.1700

Data Index: 758519 (Open Web Text)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.3912. Min Act: -0.1700

Data Index: 242721 (Open Web Text)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.3784. Min Act: -0.1700

Data Index: 3747384 (Open Web Text)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.3543. Min Act: -0.1700

Data Index: 5414151 (Open Web Text)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.3684. Min Act: -0.1700

Data Index: 5803007 (Open Web Text)

Max Activating Token Index: 308

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.5761. Min Range: -2.5761

Max Act: 2.3849. Min Act: -0.1700

Data Index: 4503091 (Open Web Text)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #19