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

Dataset: Open Web Text

Neuron 306 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: 4.6833. Min Range: -4.6833

Max Act: 4.6504. Min Act: -0.1700

Data Index: 4326665 (Open Web Text)

Max Activating Token Index: 193

Text #1

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.6833. Min Act: -0.1700

Data Index: 7282554 (Open Web Text)

Max Activating Token Index: 806

Text #2

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.6650. Min Act: -0.1700

Data Index: 2986480 (Open Web Text)

Max Activating Token Index: 836

Text #3

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.6274. Min Act: -0.1700

Data Index: 6825173 (Open Web Text)

Max Activating Token Index: 213

Text #4

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.6301. Min Act: -0.1700

Data Index: 8676149 (Open Web Text)

Max Activating Token Index: 220

Text #5

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.6401. Min Act: -0.1700

Data Index: 5932832 (Open Web Text)

Max Activating Token Index: 94

Text #6

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5953. Min Act: -0.1700

Data Index: 5252564 (Open Web Text)

Max Activating Token Index: 367

Text #7

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5865. Min Act: -0.1700

Data Index: 4255414 (Open Web Text)

Max Activating Token Index: 715

Text #8

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5928. Min Act: -0.1700

Data Index: 1247508 (Open Web Text)

Max Activating Token Index: 429

Text #9

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5781. Min Act: -0.1700

Data Index: 2565327 (Open Web Text)

Max Activating Token Index: 291

Text #10

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5344. Min Act: -0.1700

Data Index: 923427 (Open Web Text)

Max Activating Token Index: 349

Text #11

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5476. Min Act: -0.1700

Data Index: 7689587 (Open Web Text)

Max Activating Token Index: 96

Text #12

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5257. Min Act: -0.1700

Data Index: 3274393 (Open Web Text)

Max Activating Token Index: 182

Text #13

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5583. Min Act: -0.1700

Data Index: 233920 (Open Web Text)

Max Activating Token Index: 180

Text #14

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5913. Min Act: -0.1700

Data Index: 5557324 (Open Web Text)

Max Activating Token Index: 886

Text #15

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5294. Min Act: -0.1700

Data Index: 3233363 (Open Web Text)

Max Activating Token Index: 678

Text #16

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5256. Min Act: -0.1700

Data Index: 1790673 (Open Web Text)

Max Activating Token Index: 890

Text #17

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5156. Min Act: -0.1700

Data Index: 1509308 (Open Web Text)

Max Activating Token Index: 273

Text #18

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5356. Min Act: -0.1700

Data Index: 5624351 (Open Web Text)

Max Activating Token Index: 121

Text #19

Max Range: 4.6833. Min Range: -4.6833

Max Act: 4.5153. Min Act: -0.1700

Data Index: 1043442 (Open Web Text)

Max Activating Token Index: 263