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

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

Neuron 3049 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0318. Min Act: -0.0002

Data Index: 48199 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0318. Min Act: -0.0002

Data Index: 249673 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0309. Min Act: -0.0002

Data Index: 381867 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1503334 (Python Code)

Max Activating Token Index: 892

Text #4

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0314. Min Act: -0.0002

Data Index: 153279 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0301. Min Act: -0.0002

Data Index: 913316 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1638719 (Python Code)

Max Activating Token Index: 993

Text #7

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0278. Min Act: -0.0002

Data Index: 161943 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1031586 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1412879 (Python Code)

Max Activating Token Index: 342

Text #10

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0258. Min Act: -0.0002

Data Index: 384554 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0269. Min Act: -0.0002

Data Index: 688819 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1627378 (Python Code)

Max Activating Token Index: 263

Text #13

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0250. Min Act: -0.0002

Data Index: 552512 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0281. Min Act: -0.0002

Data Index: 775846 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1325751 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0245. Min Act: -0.0002

Data Index: 125492 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1632510 (Python Code)

Max Activating Token Index: 83

Text #18

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0262. Min Act: -0.0002

Data Index: 866325 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.0318. Min Range: -0.0318

Max Act: 0.0258. Min Act: -0.0002

Data Index: 702364 (C4 (Web Text))

Max Activating Token Index: 486