Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1826 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0355. Min Act: -0.0003

Data Index: 228506 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0342. Min Act: -0.0003

Data Index: 479518 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1073424 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0338. Min Act: -0.0003

Data Index: 303113 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0334. Min Act: -0.0004

Data Index: 742185 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0338. Min Act: -0.0003

Data Index: 919430 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0320. Min Act: -0.0003

Data Index: 921655 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0320. Min Act: -0.0003

Data Index: 963704 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1225936 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0321. Min Act: -0.0003

Data Index: 764781 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0308. Min Act: -0.0003

Data Index: 452542 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1090834 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0307. Min Act: -0.0003

Data Index: 425081 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1179199 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0309. Min Act: -0.0003

Data Index: 31062 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0302. Min Act: -0.0003

Data Index: 68143 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1136627 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0315. Min Act: -0.0003

Data Index: 609936 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1431667 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 0.0355. Min Range: -0.0355

Max Act: 0.0297. Min Act: -0.0003

Data Index: 533852 (C4 (Web Text))

Max Activating Token Index: 787