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

Dataset: Open Web Text

Neuron 546 in Layer 3

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: 4.3561. Min Range: -4.3561

Max Act: 4.3561. Min Act: -0.1700

Data Index: 3153050 (Open Web Text)

Max Activating Token Index: 600

Text #1

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.3302. Min Act: -0.1700

Data Index: 4078678 (Open Web Text)

Max Activating Token Index: 645

Text #2

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.3249. Min Act: -0.1700

Data Index: 7755627 (Open Web Text)

Max Activating Token Index: 34

Text #3

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.3048. Min Act: -0.1700

Data Index: 4371759 (Open Web Text)

Max Activating Token Index: 470

Text #4

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2707. Min Act: -0.1700

Data Index: 7311217 (Open Web Text)

Max Activating Token Index: 696

Text #5

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2523. Min Act: -0.1700

Data Index: 8050588 (Open Web Text)

Max Activating Token Index: 595

Text #6

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2421. Min Act: -0.1700

Data Index: 2586483 (Open Web Text)

Max Activating Token Index: 661

Text #7

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2465. Min Act: -0.1700

Data Index: 6005684 (Open Web Text)

Max Activating Token Index: 747

Text #8

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2358. Min Act: -0.1700

Data Index: 4891946 (Open Web Text)

Max Activating Token Index: 717

Text #9

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.1978. Min Act: -0.1700

Data Index: 5755564 (Open Web Text)

Max Activating Token Index: 581

Text #10

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2316. Min Act: -0.1700

Data Index: 6897568 (Open Web Text)

Max Activating Token Index: 269

Text #11

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2187. Min Act: -0.1700

Data Index: 6542713 (Open Web Text)

Max Activating Token Index: 300

Text #12

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2036. Min Act: -0.1700

Data Index: 3532594 (Open Web Text)

Max Activating Token Index: 668

Text #13

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2041. Min Act: -0.1700

Data Index: 3304747 (Open Web Text)

Max Activating Token Index: 716

Text #14

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.2025. Min Act: -0.1700

Data Index: 2449802 (Open Web Text)

Max Activating Token Index: 670

Text #15

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.1698. Min Act: -0.1700

Data Index: 2676351 (Open Web Text)

Max Activating Token Index: 342

Text #16

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.1605. Min Act: -0.1700

Data Index: 6516686 (Open Web Text)

Max Activating Token Index: 622

Text #17

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.1684. Min Act: -0.1700

Data Index: 188342 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.1742. Min Act: -0.1700

Data Index: 3571814 (Open Web Text)

Max Activating Token Index: 108

Text #19

Max Range: 4.3561. Min Range: -4.3561

Max Act: 4.1930. Min Act: -0.1700

Data Index: 5156847 (Open Web Text)

Max Activating Token Index: 643