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

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

Neuron 505 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: 0.0421. Min Range: -0.0421

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1011683 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0314. Min Act: -0.0003

Data Index: 1274974 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1112374 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0296. Min Act: -0.0003

Data Index: 848328 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0287. Min Act: -0.0002

Data Index: 516879 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0272. Min Act: -0.0003

Data Index: 566331 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0281. Min Act: -0.0003

Data Index: 908334 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0278. Min Act: -0.0003

Data Index: 260719 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0278. Min Act: -0.0003

Data Index: 508932 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1033659 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0253. Min Act: -0.0003

Data Index: 45030 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0256. Min Act: -0.0002

Data Index: 284632 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1050064 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0259. Min Act: -0.0003

Data Index: 167144 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1095347 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0264. Min Act: -0.0003

Data Index: 863847 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1333783 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0248. Min Act: -0.0003

Data Index: 988641 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0249. Min Act: -0.0003

Data Index: 616166 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0242. Min Act: -0.0003

Data Index: 771993 (C4 (Web Text))

Max Activating Token Index: 364