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

Dataset: Open Web Text

Neuron 516 in Layer 2

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: 4.2955. Min Range: -4.2955

Max Act: 4.2780. Min Act: -0.1700

Data Index: 4874717 (Open Web Text)

Max Activating Token Index: 601

Text #1

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.2955. Min Act: -0.1700

Data Index: 6208348 (Open Web Text)

Max Activating Token Index: 496

Text #2

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1552. Min Act: -0.1700

Data Index: 1606507 (Open Web Text)

Max Activating Token Index: 127

Text #3

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1816. Min Act: -0.1700

Data Index: 3690649 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1754. Min Act: -0.1700

Data Index: 6365578 (Open Web Text)

Max Activating Token Index: 513

Text #5

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1818. Min Act: -0.1700

Data Index: 3470852 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1875. Min Act: -0.1700

Data Index: 5561815 (Open Web Text)

Max Activating Token Index: 286

Text #7

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1473. Min Act: -0.1700

Data Index: 6953688 (Open Web Text)

Max Activating Token Index: 628

Text #8

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1200. Min Act: -0.1700

Data Index: 2633312 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1179. Min Act: -0.1700

Data Index: 6151022 (Open Web Text)

Max Activating Token Index: 543

Text #10

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1004. Min Act: -0.1700

Data Index: 5046799 (Open Web Text)

Max Activating Token Index: 56

Text #11

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1275. Min Act: -0.1700

Data Index: 977168 (Open Web Text)

Max Activating Token Index: 259

Text #12

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1306. Min Act: -0.1700

Data Index: 5435436 (Open Web Text)

Max Activating Token Index: 403

Text #13

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1189. Min Act: -0.1700

Data Index: 3397211 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1095. Min Act: -0.1700

Data Index: 6018081 (Open Web Text)

Max Activating Token Index: 472

Text #15

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.0976. Min Act: -0.1700

Data Index: 237031 (Open Web Text)

Max Activating Token Index: 377

Text #16

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.0673. Min Act: -0.1700

Data Index: 489969 (Open Web Text)

Max Activating Token Index: 871

Text #17

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1081. Min Act: -0.1700

Data Index: 4825548 (Open Web Text)

Max Activating Token Index: 225

Text #18

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1293. Min Act: -0.1700

Data Index: 2530348 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 4.2955. Min Range: -4.2955

Max Act: 4.1493. Min Act: -0.1700

Data Index: 4629880 (Open Web Text)

Max Activating Token Index: 912