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

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

Neuron 408 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: 0.0499. Min Range: -0.0499

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1061054 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0499. Min Act: -0.0003

Data Index: 944422 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0415. Min Act: -0.0003

Data Index: 532064 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0209. Min Act: -0.0003

Data Index: 867355 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0365. Min Act: -0.0003

Data Index: 845809 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0351. Min Act: -0.0003

Data Index: 305910 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0325. Min Act: -0.0003

Data Index: 262365 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0250. Min Act: -0.0003

Data Index: 716900 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0263. Min Act: -0.0002

Data Index: 641030 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1456964 (Python Code)

Max Activating Token Index: 879

Text #10

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0270. Min Act: -0.0003

Data Index: 930058 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1153065 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0260. Min Act: -0.0003

Data Index: 175306 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0152. Min Act: -0.0003

Data Index: 293189 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0236. Min Act: -0.0003

Data Index: 979781 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0259. Min Act: -0.0003

Data Index: 400450 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0257. Min Act: -0.0003

Data Index: 451002 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0253. Min Act: -0.0002

Data Index: 431969 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0275. Min Act: -0.0003

Data Index: 770382 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.0499. Min Range: -0.0499

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1055974 (C4 (Web Text))

Max Activating Token Index: 111