Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1433 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0397. Min Act: -0.0003

Data Index: 610867 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0366. Min Act: -0.0004

Data Index: 821475 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0327. Min Act: -0.0003

Data Index: 582382 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0331. Min Act: -0.0003

Data Index: 10831 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0322. Min Act: -0.0003

Data Index: 85372 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0302. Min Act: -0.0004

Data Index: 323218 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0306. Min Act: -0.0004

Data Index: 920338 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0304. Min Act: -0.0003

Data Index: 291122 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0312. Min Act: -0.0003

Data Index: 97603 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0294. Min Act: -0.0004

Data Index: 33191 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1248835 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0297. Min Act: -0.0003

Data Index: 192105 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0307. Min Act: -0.0003

Data Index: 192041 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0292. Min Act: -0.0003

Data Index: 114334 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1284248 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1183440 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0301. Min Act: -0.0003

Data Index: 482144 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0288. Min Act: -0.0004

Data Index: 894409 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1123361 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.0397. Min Range: -0.0397

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1116959 (C4 (Web Text))

Max Activating Token Index: 415