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

Dataset: Open Web Text

Neuron 1575 in Layer 4

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: 5.2294. Min Range: -5.2294

Max Act: 5.2294. Min Act: -0.1700

Data Index: 6734173 (Open Web Text)

Max Activating Token Index: 997

Text #1

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.1704. Min Act: -0.1700

Data Index: 290406 (Open Web Text)

Max Activating Token Index: 938

Text #2

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.1785. Min Act: -0.1700

Data Index: 448991 (Open Web Text)

Max Activating Token Index: 158

Text #3

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0624. Min Act: -0.1700

Data Index: 5597258 (Open Web Text)

Max Activating Token Index: 382

Text #4

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0980. Min Act: -0.1700

Data Index: 1815480 (Open Web Text)

Max Activating Token Index: 644

Text #5

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0501. Min Act: -0.1700

Data Index: 124430 (Open Web Text)

Max Activating Token Index: 156

Text #6

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0503. Min Act: -0.1700

Data Index: 8273277 (Open Web Text)

Max Activating Token Index: 354

Text #7

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0500. Min Act: -0.1700

Data Index: 7767379 (Open Web Text)

Max Activating Token Index: 131

Text #8

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0351. Min Act: -0.1700

Data Index: 8729811 (Open Web Text)

Max Activating Token Index: 415

Text #9

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0685. Min Act: -0.1700

Data Index: 4575578 (Open Web Text)

Max Activating Token Index: 785

Text #10

Max Range: 5.2294. Min Range: -5.2294

Max Act: 4.9914. Min Act: -0.1700

Data Index: 2263454 (Open Web Text)

Max Activating Token Index: 1017

Text #11

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0246. Min Act: -0.1700

Data Index: 4544849 (Open Web Text)

Max Activating Token Index: 420

Text #12

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0210. Min Act: -0.1700

Data Index: 3840857 (Open Web Text)

Max Activating Token Index: 405

Text #13

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0248. Min Act: -0.1700

Data Index: 2338263 (Open Web Text)

Max Activating Token Index: 45

Text #14

Max Range: 5.2294. Min Range: -5.2294

Max Act: 4.9889. Min Act: -0.1700

Data Index: 1192421 (Open Web Text)

Max Activating Token Index: 272

Text #15

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0129. Min Act: -0.1700

Data Index: 3411244 (Open Web Text)

Max Activating Token Index: 113

Text #16

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0247. Min Act: -0.1700

Data Index: 705696 (Open Web Text)

Max Activating Token Index: 979

Text #17

Max Range: 5.2294. Min Range: -5.2294

Max Act: 4.9812. Min Act: -0.1700

Data Index: 6837136 (Open Web Text)

Max Activating Token Index: 977

Text #18

Max Range: 5.2294. Min Range: -5.2294

Max Act: 4.9929. Min Act: -0.1700

Data Index: 8630412 (Open Web Text)

Max Activating Token Index: 615

Text #19

Max Range: 5.2294. Min Range: -5.2294

Max Act: 5.0168. Min Act: -0.1700

Data Index: 4807517 (Open Web Text)

Max Activating Token Index: 357