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

Dataset: Open Web Text

Neuron 1866 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: 4.7119. Min Range: -4.7119

Max Act: 4.7119. Min Act: -0.1700

Data Index: 6509830 (Open Web Text)

Max Activating Token Index: 208

Text #1

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6798. Min Act: -0.1700

Data Index: 379839 (Open Web Text)

Max Activating Token Index: 354

Text #2

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6622. Min Act: -0.1700

Data Index: 5696555 (Open Web Text)

Max Activating Token Index: 292

Text #3

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6476. Min Act: -0.1700

Data Index: 82019 (Open Web Text)

Max Activating Token Index: 366

Text #4

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6662. Min Act: -0.1700

Data Index: 8247591 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6527. Min Act: -0.1700

Data Index: 3575152 (Open Web Text)

Max Activating Token Index: 28

Text #6

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6333. Min Act: -0.1700

Data Index: 4874028 (Open Web Text)

Max Activating Token Index: 313

Text #7

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6423. Min Act: -0.1700

Data Index: 95070 (Open Web Text)

Max Activating Token Index: 271

Text #8

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6175. Min Act: -0.1700

Data Index: 1250546 (Open Web Text)

Max Activating Token Index: 159

Text #9

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6423. Min Act: -0.1700

Data Index: 4080518 (Open Web Text)

Max Activating Token Index: 325

Text #10

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6400. Min Act: -0.1700

Data Index: 325217 (Open Web Text)

Max Activating Token Index: 232

Text #11

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6274. Min Act: -0.1700

Data Index: 5967588 (Open Web Text)

Max Activating Token Index: 111

Text #12

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6505. Min Act: -0.1700

Data Index: 5790302 (Open Web Text)

Max Activating Token Index: 219

Text #13

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6134. Min Act: -0.1700

Data Index: 636766 (Open Web Text)

Max Activating Token Index: 294

Text #14

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6265. Min Act: -0.1700

Data Index: 2141446 (Open Web Text)

Max Activating Token Index: 361

Text #15

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6165. Min Act: -0.1700

Data Index: 4412647 (Open Web Text)

Max Activating Token Index: 827

Text #16

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.5876. Min Act: -0.1700

Data Index: 3898595 (Open Web Text)

Max Activating Token Index: 232

Text #17

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6130. Min Act: -0.1700

Data Index: 4098235 (Open Web Text)

Max Activating Token Index: 302

Text #18

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.5873. Min Act: -0.1700

Data Index: 4291898 (Open Web Text)

Max Activating Token Index: 604

Text #19

Max Range: 4.7119. Min Range: -4.7119

Max Act: 4.6028. Min Act: -0.1700

Data Index: 243729 (Open Web Text)

Max Activating Token Index: 394