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

Dataset: Open Web Text

Neuron 212 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: 4.8177. Min Range: -4.8177

Max Act: 4.8177. Min Act: -0.1700

Data Index: 3666806 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7944. Min Act: -0.1700

Data Index: 1569624 (Open Web Text)

Max Activating Token Index: 172

Text #2

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7620. Min Act: -0.1700

Data Index: 5064354 (Open Web Text)

Max Activating Token Index: 544

Text #3

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7783. Min Act: -0.1700

Data Index: 762733 (Open Web Text)

Max Activating Token Index: 628

Text #4

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7824. Min Act: -0.1700

Data Index: 2452007 (Open Web Text)

Max Activating Token Index: 266

Text #5

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7635. Min Act: -0.1700

Data Index: 2763369 (Open Web Text)

Max Activating Token Index: 921

Text #6

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7874. Min Act: -0.1700

Data Index: 6459545 (Open Web Text)

Max Activating Token Index: 112

Text #7

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7847. Min Act: -0.1700

Data Index: 5388213 (Open Web Text)

Max Activating Token Index: 573

Text #8

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7431. Min Act: -0.1700

Data Index: 3366618 (Open Web Text)

Max Activating Token Index: 826

Text #9

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7549. Min Act: -0.1700

Data Index: 1661341 (Open Web Text)

Max Activating Token Index: 913

Text #10

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7487. Min Act: -0.1700

Data Index: 6978520 (Open Web Text)

Max Activating Token Index: 94

Text #11

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7684. Min Act: -0.1700

Data Index: 3439141 (Open Web Text)

Max Activating Token Index: 281

Text #12

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7201. Min Act: -0.1700

Data Index: 2647809 (Open Web Text)

Max Activating Token Index: 165

Text #13

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7094. Min Act: -0.1700

Data Index: 3932090 (Open Web Text)

Max Activating Token Index: 643

Text #14

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7294. Min Act: -0.1700

Data Index: 2348933 (Open Web Text)

Max Activating Token Index: 692

Text #15

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.6674. Min Act: -0.1700

Data Index: 4904175 (Open Web Text)

Max Activating Token Index: 457

Text #16

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.6982. Min Act: -0.1700

Data Index: 7062134 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7165. Min Act: -0.1700

Data Index: 7426685 (Open Web Text)

Max Activating Token Index: 790

Text #18

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7102. Min Act: -0.1700

Data Index: 2160429 (Open Web Text)

Max Activating Token Index: 1012

Text #19

Max Range: 4.8177. Min Range: -4.8177

Max Act: 4.7319. Min Act: -0.1700

Data Index: 4529398 (Open Web Text)

Max Activating Token Index: 738