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

Dataset: Open Web Text

Neuron 1911 in Layer 1

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: 4.1218. Min Range: -4.1218

Max Act: 4.0965. Min Act: -0.1700

Data Index: 8286812 (Open Web Text)

Max Activating Token Index: 948

Text #1

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.1218. Min Act: -0.1700

Data Index: 6593120 (Open Web Text)

Max Activating Token Index: 268

Text #2

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.1033. Min Act: -0.1700

Data Index: 3041815 (Open Web Text)

Max Activating Token Index: 532

Text #3

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0628. Min Act: -0.1700

Data Index: 8566048 (Open Web Text)

Max Activating Token Index: 294

Text #4

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0302. Min Act: -0.1700

Data Index: 46099 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0428. Min Act: -0.1700

Data Index: 6797550 (Open Web Text)

Max Activating Token Index: 634

Text #6

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0294. Min Act: -0.1700

Data Index: 8353979 (Open Web Text)

Max Activating Token Index: 299

Text #7

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0508. Min Act: -0.1700

Data Index: 8656034 (Open Web Text)

Max Activating Token Index: 967

Text #8

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0247. Min Act: -0.1700

Data Index: 432595 (Open Web Text)

Max Activating Token Index: 314

Text #9

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0095. Min Act: -0.1700

Data Index: 1750159 (Open Web Text)

Max Activating Token Index: 389

Text #10

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0125. Min Act: -0.1700

Data Index: 3178278 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0077. Min Act: -0.1700

Data Index: 1929305 (Open Web Text)

Max Activating Token Index: 153

Text #12

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9962. Min Act: -0.1700

Data Index: 862335 (Open Web Text)

Max Activating Token Index: 443

Text #13

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0199. Min Act: -0.1700

Data Index: 3564769 (Open Web Text)

Max Activating Token Index: 375

Text #14

Max Range: 4.1218. Min Range: -4.1218

Max Act: 3.9988. Min Act: -0.1700

Data Index: 936227 (Open Web Text)

Max Activating Token Index: 574

Text #15

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0066. Min Act: -0.1700

Data Index: 3829643 (Open Web Text)

Max Activating Token Index: 824

Text #16

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0191. Min Act: -0.1700

Data Index: 4111599 (Open Web Text)

Max Activating Token Index: 340

Text #17

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0106. Min Act: -0.1700

Data Index: 5575397 (Open Web Text)

Max Activating Token Index: 679

Text #18

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0034. Min Act: -0.1700

Data Index: 6254539 (Open Web Text)

Max Activating Token Index: 870

Text #19

Max Range: 4.1218. Min Range: -4.1218

Max Act: 4.0006. Min Act: -0.1700

Data Index: 1011208 (Open Web Text)

Max Activating Token Index: 742