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

Dataset: Open Web Text

Neuron 1508 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: 6.0280. Min Range: -6.0280

Max Act: 6.0280. Min Act: -0.1700

Data Index: 4725406 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.8143. Min Act: -0.1700

Data Index: 5691698 (Open Web Text)

Max Activating Token Index: 128

Text #2

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.7863. Min Act: -0.1700

Data Index: 4251182 (Open Web Text)

Max Activating Token Index: 116

Text #3

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.7816. Min Act: -0.1700

Data Index: 8340242 (Open Web Text)

Max Activating Token Index: 377

Text #4

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.7488. Min Act: -0.1700

Data Index: 3400993 (Open Web Text)

Max Activating Token Index: 196

Text #5

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.7107. Min Act: -0.1700

Data Index: 4815332 (Open Web Text)

Max Activating Token Index: 192

Text #6

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.5710. Min Act: -0.1700

Data Index: 1339461 (Open Web Text)

Max Activating Token Index: 147

Text #7

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.5015. Min Act: -0.1700

Data Index: 4424178 (Open Web Text)

Max Activating Token Index: 525

Text #8

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.5185. Min Act: -0.1700

Data Index: 3161477 (Open Web Text)

Max Activating Token Index: 310

Text #9

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.4191. Min Act: -0.1700

Data Index: 3147248 (Open Web Text)

Max Activating Token Index: 237

Text #10

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.4488. Min Act: -0.1700

Data Index: 5210077 (Open Web Text)

Max Activating Token Index: 142

Text #11

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.4227. Min Act: -0.1700

Data Index: 1077576 (Open Web Text)

Max Activating Token Index: 338

Text #12

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.4681. Min Act: -0.1700

Data Index: 4712724 (Open Web Text)

Max Activating Token Index: 190

Text #13

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.4308. Min Act: -0.1700

Data Index: 1713273 (Open Web Text)

Max Activating Token Index: 327

Text #14

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.4149. Min Act: -0.1700

Data Index: 2715188 (Open Web Text)

Max Activating Token Index: 271

Text #15

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.3898. Min Act: -0.1700

Data Index: 1439279 (Open Web Text)

Max Activating Token Index: 582

Text #16

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.3565. Min Act: -0.1696

Data Index: 5765808 (Open Web Text)

Max Activating Token Index: 252

Text #17

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.3907. Min Act: -0.1698

Data Index: 2720812 (Open Web Text)

Max Activating Token Index: 433

Text #18

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.3029. Min Act: -0.1699

Data Index: 8221124 (Open Web Text)

Max Activating Token Index: 35

Text #19

Max Range: 6.0280. Min Range: -6.0280

Max Act: 5.3031. Min Act: -0.1700

Data Index: 1327855 (Open Web Text)

Max Activating Token Index: 565