Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1760 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1048831 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0255. Min Act: -0.0006

Data Index: 541245 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0240. Min Act: -0.0006

Data Index: 897205 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0243. Min Act: -0.0006

Data Index: 1192946 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0239. Min Act: -0.0006

Data Index: 956093 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0239. Min Act: -0.0006

Data Index: 780015 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0237. Min Act: -0.0006

Data Index: 157123 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0235. Min Act: -0.0006

Data Index: 125762 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0228. Min Act: -0.0006

Data Index: 453412 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0231. Min Act: -0.0006

Data Index: 578280 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0228. Min Act: -0.0006

Data Index: 835207 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0234. Min Act: -0.0006

Data Index: 644614 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0226. Min Act: -0.0006

Data Index: 706138 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0225. Min Act: -0.0006

Data Index: 552078 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0225. Min Act: -0.0006

Data Index: 519618 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0223. Min Act: -0.0005

Data Index: 1294394 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0217. Min Act: -0.0006

Data Index: 43317 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0220. Min Act: -0.0005

Data Index: 412073 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0217. Min Act: -0.0006

Data Index: 714128 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 0.0317. Min Range: -0.0317

Max Act: 0.0213. Min Act: -0.0006

Data Index: 1318285 (C4 (Web Text))

Max Activating Token Index: 58