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

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

Neuron 4372 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1404878 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1481125 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1457319 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1584706 (Python Code)

Max Activating Token Index: 292

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1440553 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1603497 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0227. Min Act: -0.0002

Data Index: 1617990 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1568048 (Python Code)

Max Activating Token Index: 958

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1371561 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0238. Min Act: -0.0002

Data Index: 506832 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1502181 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1496921 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1462307 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1529593 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1545817 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1426292 (Python Code)

Max Activating Token Index: 6

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1363169 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1465172 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1547720 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1435570 (Python Code)

Max Activating Token Index: 6