Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1610 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0001

Data Index: 1168471 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0291. Min Act: -0.0001

Data Index: 392556 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0279. Min Act: -0.0001

Data Index: 200218 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0256. Min Act: -0.0001

Data Index: 254053 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0261. Min Act: -0.0001

Data Index: 587671 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0259. Min Act: -0.0001

Data Index: 356026 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0252. Min Act: -0.0001

Data Index: 240796 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0248. Min Act: -0.0001

Data Index: 861020 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0255. Min Act: -0.0001

Data Index: 980379 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0239. Min Act: -0.0001

Data Index: 817880 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0237. Min Act: -0.0001

Data Index: 213209 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1102527 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1326523 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0234. Min Act: -0.0001

Data Index: 424735 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0226. Min Act: -0.0001

Data Index: 856201 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0231. Min Act: -0.0001

Data Index: 280115 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0234. Min Act: -0.0001

Data Index: 858264 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0216. Min Act: -0.0001

Data Index: 61118 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0228. Min Act: -0.0001

Data Index: 375096 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0225. Min Act: -0.0001

Data Index: 257392 (C4 (Web Text))

Max Activating Token Index: 38