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

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

Neuron 2242 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0001

Data Index: 610946 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0357. Min Act: -0.0001

Data Index: 983192 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1138916 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0332. Min Act: -0.0001

Data Index: 662915 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0344. Min Act: -0.0001

Data Index: 656419 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0330. Min Act: -0.0001

Data Index: 253283 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0313. Min Act: -0.0001

Data Index: 422399 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0335. Min Act: -0.0001

Data Index: 382239 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1115823 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0286. Min Act: -0.0001

Data Index: 990105 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0318. Min Act: -0.0001

Data Index: 623342 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0306. Min Act: -0.0001

Data Index: 105824 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0312. Min Act: -0.0001

Data Index: 508334 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0311. Min Act: -0.0001

Data Index: 395886 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1163324 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1139343 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0284. Min Act: -0.0001

Data Index: 80932 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0258. Min Act: -0.0001

Data Index: 301832 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0317. Min Act: -0.0001

Data Index: 537778 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0271. Min Act: -0.0001

Data Index: 561770 (C4 (Web Text))

Max Activating Token Index: 794