< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 3038 in Layer 1

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: 2.3621. Min Range: -2.3621

Max Act: 2.3621. Min Act: -0.1700

Data Index: 3642913 (Open Web Text)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.3120. Min Act: -0.1693

Data Index: 2948670 (Open Web Text)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.3083. Min Act: -0.1700

Data Index: 2168934 (Open Web Text)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.3046. Min Act: -0.1700

Data Index: 4476876 (Open Web Text)

Max Activating Token Index: 773

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2837. Min Act: -0.1700

Data Index: 3193723 (Open Web Text)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2865. Min Act: -0.1700

Data Index: 5826464 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2626. Min Act: -0.1700

Data Index: 4888007 (Open Web Text)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2640. Min Act: -0.1700

Data Index: 3735486 (Open Web Text)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2682. Min Act: -0.1700

Data Index: 1427532 (Open Web Text)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2694. Min Act: -0.1700

Data Index: 7492246 (Open Web Text)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2594. Min Act: -0.1700

Data Index: 7785947 (Open Web Text)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2479. Min Act: -0.1700

Data Index: 604140 (Open Web Text)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2471. Min Act: -0.1700

Data Index: 1390442 (Open Web Text)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2466. Min Act: -0.1700

Data Index: 2279261 (Open Web Text)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2521. Min Act: -0.1700

Data Index: 3887172 (Open Web Text)

Max Activating Token Index: 607

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2458. Min Act: -0.1700

Data Index: 891111 (Open Web Text)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2424. Min Act: -0.1700

Data Index: 319626 (Open Web Text)

Max Activating Token Index: 422

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2328. Min Act: -0.1700

Data Index: 5662493 (Open Web Text)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2335. Min Act: -0.1700

Data Index: 4637437 (Open Web Text)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3621. Min Range: -2.3621

Max Act: 2.2344. Min Act: -0.1700

Data Index: 2055209 (Open Web Text)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #19