Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5187 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0343. Min Act: -0.0001

Data Index: 220664 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0318. Min Act: -0.0002

Data Index: 340906 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1210715 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0320. Min Act: -0.0001

Data Index: 203275 (C4 (Web Text))

Max Activating Token Index: 52

Text #4

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1203382 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1461683 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1327796 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1628713 (Python Code)

Max Activating Token Index: 597

Text #8

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0287. Min Act: -0.0002

Data Index: 240111 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1400605 (Python Code)

Max Activating Token Index: 408

Text #10

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0211. Min Act: -0.0001

Data Index: 968852 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0273. Min Act: -0.0001

Data Index: 1298436 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0243. Min Act: -0.0001

Data Index: 977400 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1150358 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1428687 (Python Code)

Max Activating Token Index: 547

Text #15

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0231. Min Act: -0.0001

Data Index: 991289 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1125995 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1186715 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0244. Min Act: -0.0001

Data Index: 780972 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0245. Min Act: -0.0001

Data Index: 386649 (C4 (Web Text))

Max Activating Token Index: 329