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

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

Neuron 3808 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: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0002

Data Index: 249300 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1255392 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0318. Min Act: -0.0002

Data Index: 705292 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0307. Min Act: -0.0002

Data Index: 236186 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1098961 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1076620 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0308. Min Act: -0.0002

Data Index: 266729 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1012937 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0308. Min Act: -0.0002

Data Index: 808922 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0308. Min Act: -0.0002

Data Index: 756283 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0307. Min Act: -0.0002

Data Index: 182777 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1109592 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0308. Min Act: -0.0002

Data Index: 278891 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1034955 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1127181 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1203143 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1284345 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0301. Min Act: -0.0002

Data Index: 75353 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1203171 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1286782 (C4 (Web Text))

Max Activating Token Index: 220