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

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

Neuron 2983 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: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0002

Data Index: 632673 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1109242 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0308. Min Act: -0.0002

Data Index: 901307 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1003526 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0292. Min Act: -0.0002

Data Index: 534469 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0289. Min Act: -0.0002

Data Index: 399191 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0282. Min Act: -0.0003

Data Index: 435490 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0288. Min Act: -0.0002

Data Index: 196166 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0281. Min Act: -0.0003

Data Index: 792352 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0278. Min Act: -0.0002

Data Index: 851291 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0271. Min Act: -0.0002

Data Index: 162918 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0273. Min Act: -0.0003

Data Index: 162949 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1197364 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0265. Min Act: -0.0003

Data Index: 86874 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1165612 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0259. Min Act: -0.0003

Data Index: 458807 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0254. Min Act: -0.0003

Data Index: 801721 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0264. Min Act: -0.0002

Data Index: 720274 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0262. Min Act: -0.0003

Data Index: 724173 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1183338 (C4 (Web Text))

Max Activating Token Index: 891