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

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

Neuron 3854 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1126439 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0276. Min Act: -0.0002

Data Index: 476808 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0274. Min Act: -0.0002

Data Index: 715258 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1049256 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0270. Min Act: -0.0002

Data Index: 665999 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1330215 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0267. Min Act: -0.0002

Data Index: 999930 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0259. Min Act: -0.0002

Data Index: 226449 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0249. Min Act: -0.0002

Data Index: 307949 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0242. Min Act: -0.0002

Data Index: 8344 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0238. Min Act: -0.0002

Data Index: 6741 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1268734 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1091886 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0240. Min Act: -0.0002

Data Index: 218496 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1190416 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0239. Min Act: -0.0002

Data Index: 502024 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0244. Min Act: -0.0002

Data Index: 292643 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1356968 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1073177 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1124918 (C4 (Web Text))

Max Activating Token Index: 191