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

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

Neuron 3414 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1481449 (Python Code)

Max Activating Token Index: 370

Text #1

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1456727 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0332. Min Act: -0.0003

Data Index: 165959 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0328. Min Act: -0.0003

Data Index: 1362788 (Python Code)

Max Activating Token Index: 725

Text #4

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1494621 (Python Code)

Max Activating Token Index: 377

Text #5

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1530080 (Python Code)

Max Activating Token Index: 957

Text #6

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1493306 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1376040 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1572085 (Python Code)

Max Activating Token Index: 772

Text #9

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0255. Min Act: -0.0003

Data Index: 136133 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1578989 (Python Code)

Max Activating Token Index: 372

Text #11

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1545694 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1442770 (Python Code)

Max Activating Token Index: 330

Text #13

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1411024 (Python Code)

Max Activating Token Index: 427

Text #14

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1381358 (Python Code)

Max Activating Token Index: 917

Text #15

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1542888 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1379217 (Python Code)

Max Activating Token Index: 220

Text #17

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1510898 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1523351 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 0.0430. Min Range: -0.0430

Max Act: 0.0233. Min Act: -0.0003

Data Index: 1395920 (Python Code)

Max Activating Token Index: 552