Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2580 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0328. Min Act: -0.0003

Data Index: 881821 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0336. Min Act: -0.0003

Data Index: 868541 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0309. Min Act: -0.0003

Data Index: 157853 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0308. Min Act: -0.0003

Data Index: 898001 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0303. Min Act: -0.0003

Data Index: 35406 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0302. Min Act: -0.0003

Data Index: 181278 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0288. Min Act: -0.0002

Data Index: 283135 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0291. Min Act: -0.0003

Data Index: 691197 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0286. Min Act: -0.0002

Data Index: 108918 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0290. Min Act: -0.0002

Data Index: 154105 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1051115 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0286. Min Act: -0.0003

Data Index: 14925 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0285. Min Act: -0.0003

Data Index: 257453 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0284. Min Act: -0.0002

Data Index: 122429 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0282. Min Act: -0.0003

Data Index: 865406 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0284. Min Act: -0.0002

Data Index: 505422 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0284. Min Act: -0.0002

Data Index: 330215 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0282. Min Act: -0.0003

Data Index: 425565 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0276. Min Act: -0.0003

Data Index: 764763 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0336. Min Range: -0.0336

Max Act: 0.0288. Min Act: -0.0002

Data Index: 870646 (C4 (Web Text))

Max Activating Token Index: 838