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

Dataset: Open Web Text

Neuron 1746 in Layer 6

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: 4.0145. Min Range: -4.0145

Max Act: 4.0145. Min Act: -0.1700

Data Index: 6366048 (Open Web Text)

Max Activating Token Index: 963

Text #1

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.9275. Min Act: -0.1700

Data Index: 4336852 (Open Web Text)

Max Activating Token Index: 636

Text #2

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.9172. Min Act: -0.1700

Data Index: 5345761 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8184. Min Act: -0.1700

Data Index: 7575899 (Open Web Text)

Max Activating Token Index: 731

Text #4

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8696. Min Act: -0.1700

Data Index: 3086991 (Open Web Text)

Max Activating Token Index: 373

Text #5

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8337. Min Act: -0.1700

Data Index: 3732688 (Open Web Text)

Max Activating Token Index: 619

Text #6

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8435. Min Act: -0.1700

Data Index: 6876839 (Open Web Text)

Max Activating Token Index: 1002

Text #7

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8349. Min Act: -0.1700

Data Index: 77119 (Open Web Text)

Max Activating Token Index: 746

Text #8

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8284. Min Act: -0.1700

Data Index: 7791630 (Open Web Text)

Max Activating Token Index: 724

Text #9

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8124. Min Act: -0.1700

Data Index: 3459358 (Open Web Text)

Max Activating Token Index: 585

Text #10

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8268. Min Act: -0.1700

Data Index: 2979643 (Open Web Text)

Max Activating Token Index: 445

Text #11

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8047. Min Act: -0.1700

Data Index: 3112426 (Open Web Text)

Max Activating Token Index: 454

Text #12

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8190. Min Act: -0.1700

Data Index: 2927922 (Open Web Text)

Max Activating Token Index: 783

Text #13

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7940. Min Act: -0.1700

Data Index: 2745954 (Open Web Text)

Max Activating Token Index: 336

Text #14

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8154. Min Act: -0.1700

Data Index: 245195 (Open Web Text)

Max Activating Token Index: 570

Text #15

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7907. Min Act: -0.1700

Data Index: 5475307 (Open Web Text)

Max Activating Token Index: 513

Text #16

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.8195. Min Act: -0.1700

Data Index: 2964566 (Open Web Text)

Max Activating Token Index: 811

Text #17

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7784. Min Act: -0.1700

Data Index: 2488314 (Open Web Text)

Max Activating Token Index: 244

Text #18

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7890. Min Act: -0.1700

Data Index: 3252005 (Open Web Text)

Max Activating Token Index: 970

Text #19

Max Range: 4.0145. Min Range: -4.0145

Max Act: 3.7682. Min Act: -0.1700

Data Index: 5881606 (Open Web Text)

Max Activating Token Index: 566