Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3504 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0346. Min Act: -0.0003

Data Index: 297966 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0378. Min Act: -0.0003

Data Index: 820097 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0330. Min Act: -0.0003

Data Index: 847144 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0329. Min Act: -0.0003

Data Index: 634816 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0313. Min Act: -0.0003

Data Index: 545518 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0278. Min Act: -0.0003

Data Index: 234344 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0315. Min Act: -0.0003

Data Index: 974810 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0335. Min Act: -0.0003

Data Index: 902363 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0313. Min Act: -0.0004

Data Index: 1016831 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1527145 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0292. Min Act: -0.0003

Data Index: 250330 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0355. Min Act: -0.0003

Data Index: 680312 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0281. Min Act: -0.0003

Data Index: 517415 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0263. Min Act: -0.0003

Data Index: 39910 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0299. Min Act: -0.0003

Data Index: 991396 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1235629 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0286. Min Act: -0.0003

Data Index: 611540 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0266. Min Act: -0.0003

Data Index: 315375 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0275. Min Act: -0.0003

Data Index: 970706 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0244. Min Act: -0.0003

Data Index: 223504 (C4 (Web Text))

Max Activating Token Index: 567