Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3091 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0002

Data Index: 832924 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0300. Min Act: -0.0001

Data Index: 430979 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0324. Min Act: -0.0002

Data Index: 453431 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0305. Min Act: -0.0002

Data Index: 98588 (C4 (Web Text))

Max Activating Token Index: 634

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0271. Min Act: -0.0002

Data Index: 413096 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0279. Min Act: -0.0002

Data Index: 952523 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0258. Min Act: -0.0002

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1626701 (Python Code)

Max Activating Token Index: 584

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0250. Min Act: -0.0002

Data Index: 645724 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0249. Min Act: -0.0002

Data Index: 285570 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1378912 (Python Code)

Max Activating Token Index: 502

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1119263 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1277726 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0245. Min Act: -0.0002

Data Index: 912021 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0253. Min Act: -0.0002

Data Index: 294734 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0254. Min Act: -0.0002

Data Index: 626028 (C4 (Web Text))

Max Activating Token Index: 680

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0223. Min Act: -0.0002

Data Index: 751432 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0244. Min Act: -0.0001

Data Index: 1427697 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0243. Min Act: -0.0002

Data Index: 271198 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1242430 (C4 (Web Text))

Max Activating Token Index: 97