Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 858 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0002

Data Index: 50315 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0363. Min Act: -0.0002

Data Index: 367663 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1337010 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1127470 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0346. Min Act: -0.0002

Data Index: 100718 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0336. Min Act: -0.0002

Data Index: 91478 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0348. Min Act: -0.0002

Data Index: 994180 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0345. Min Act: -0.0002

Data Index: 67610 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0341. Min Act: -0.0002

Data Index: 602925 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0331. Min Act: -0.0002

Data Index: 99541 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0329. Min Act: -0.0002

Data Index: 340910 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1130927 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1168632 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0335. Min Act: -0.0002

Data Index: 599955 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0321. Min Act: -0.0003

Data Index: 405420 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0320. Min Act: -0.0002

Data Index: 422420 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0318. Min Act: -0.0001

Data Index: 765034 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0318. Min Act: -0.0002

Data Index: 735458 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0322. Min Act: -0.0003

Data Index: 316244 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0322. Min Act: -0.0002

Data Index: 239910 (C4 (Web Text))

Max Activating Token Index: 470