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

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

Neuron 4035 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: 0.0257. Min Range: -0.0257

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1049686 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0256. Min Act: -0.0002

Data Index: 523386 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1113085 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1023479 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0249. Min Act: -0.0002

Data Index: 590919 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0248. Min Act: -0.0002

Data Index: 196757 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0253. Min Act: -0.0002

Data Index: 413097 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0247. Min Act: -0.0002

Data Index: 564911 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0247. Min Act: -0.0002

Data Index: 322602 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1357424 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0250. Min Act: -0.0002

Data Index: 959928 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0240. Min Act: -0.0001

Data Index: 1083870 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0244. Min Act: -0.0001

Data Index: 147784 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0249. Min Act: -0.0002

Data Index: 372739 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1218192 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0243. Min Act: -0.0002

Data Index: 834846 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0243. Min Act: -0.0002

Data Index: 287567 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0243. Min Act: -0.0002

Data Index: 151802 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0242. Min Act: -0.0002

Data Index: 873151 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.0257. Min Range: -0.0257

Max Act: 0.0247. Min Act: -0.0002

Data Index: 735270 (C4 (Web Text))

Max Activating Token Index: 205