< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2263 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: 2.4492. Min Range: -2.4492

Max Act: 2.3964. Min Act: -0.1700

Data Index: 5518507 (Open Web Text)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.4492. Min Act: -0.1700

Data Index: 5383445 (Open Web Text)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3736. Min Act: -0.1700

Data Index: 3267448 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3820. Min Act: -0.1700

Data Index: 37011 (Open Web Text)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3614. Min Act: -0.1700

Data Index: 5518508 (Open Web Text)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3176. Min Act: -0.1700

Data Index: 1605436 (Open Web Text)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3311. Min Act: -0.1700

Data Index: 1765433 (Open Web Text)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3179. Min Act: -0.1700

Data Index: 4259738 (Open Web Text)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3057. Min Act: -0.1700

Data Index: 4986089 (Open Web Text)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3116. Min Act: -0.1700

Data Index: 2341203 (Open Web Text)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3017. Min Act: -0.1700

Data Index: 6120818 (Open Web Text)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.2976. Min Act: -0.1700

Data Index: 306668 (Open Web Text)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.3097. Min Act: -0.1700

Data Index: 2695780 (Open Web Text)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.2884. Min Act: -0.1700

Data Index: 3802662 (Open Web Text)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.2762. Min Act: -0.1700

Data Index: 1571377 (Open Web Text)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.2668. Min Act: -0.1700

Data Index: 5381816 (Open Web Text)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.2682. Min Act: -0.1700

Data Index: 8416085 (Open Web Text)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.2607. Min Act: -0.1700

Data Index: 6772867 (Open Web Text)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.2634. Min Act: -0.1700

Data Index: 5987612 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4492. Min Range: -2.4492

Max Act: 2.2776. Min Act: -0.1700

Data Index: 4367340 (Open Web Text)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #19