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

Dataset: Open Web Text

Neuron 327 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: 3.4224. Min Range: -3.4224

Max Act: 3.4090. Min Act: -0.1700

Data Index: 1578770 (Open Web Text)

Max Activating Token Index: 547

Text #1

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.4224. Min Act: -0.1700

Data Index: 3365866 (Open Web Text)

Max Activating Token Index: 724

Text #2

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3598. Min Act: -0.1700

Data Index: 8241588 (Open Web Text)

Max Activating Token Index: 768

Text #3

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3555. Min Act: -0.1700

Data Index: 1773157 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3520. Min Act: -0.1700

Data Index: 695033 (Open Web Text)

Max Activating Token Index: 475

Text #5

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3514. Min Act: -0.1700

Data Index: 7226270 (Open Web Text)

Max Activating Token Index: 219

Text #6

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3289. Min Act: -0.1700

Data Index: 5118278 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3170. Min Act: -0.1700

Data Index: 2391915 (Open Web Text)

Max Activating Token Index: 186

Text #8

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1906449 (Open Web Text)

Max Activating Token Index: 629

Text #9

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3323. Min Act: -0.1700

Data Index: 5318789 (Open Web Text)

Max Activating Token Index: 756

Text #10

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3073. Min Act: -0.1700

Data Index: 1078099 (Open Web Text)

Max Activating Token Index: 539

Text #11

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3002. Min Act: -0.1700

Data Index: 5550923 (Open Web Text)

Max Activating Token Index: 584

Text #12

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.2921. Min Act: -0.1700

Data Index: 26995 (Open Web Text)

Max Activating Token Index: 764

Text #13

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3092. Min Act: -0.1700

Data Index: 4769395 (Open Web Text)

Max Activating Token Index: 507

Text #14

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3062. Min Act: -0.1700

Data Index: 8576265 (Open Web Text)

Max Activating Token Index: 630

Text #15

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.2941. Min Act: -0.1700

Data Index: 4245252 (Open Web Text)

Max Activating Token Index: 484

Text #16

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3048. Min Act: -0.1700

Data Index: 5727138 (Open Web Text)

Max Activating Token Index: 408

Text #17

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.3119. Min Act: -0.1700

Data Index: 8429143 (Open Web Text)

Max Activating Token Index: 894

Text #18

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.2989. Min Act: -0.1700

Data Index: 778936 (Open Web Text)

Max Activating Token Index: 504

Text #19

Max Range: 3.4224. Min Range: -3.4224

Max Act: 3.2970. Min Act: -0.1700

Data Index: 2308175 (Open Web Text)

Max Activating Token Index: 608