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

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

Neuron 57 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: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0003

Data Index: 877113 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1163967 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0305. Min Act: -0.0003

Data Index: 877978 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0285. Min Act: -0.0003

Data Index: 654027 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1197038 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0287. Min Act: -0.0003

Data Index: 850272 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0276. Min Act: -0.0003

Data Index: 715405 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1160315 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0270. Min Act: -0.0003

Data Index: 936999 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0259. Min Act: -0.0002

Data Index: 914778 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0252. Min Act: -0.0003

Data Index: 612434 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0248. Min Act: -0.0003

Data Index: 948725 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0253. Min Act: -0.0003

Data Index: 913348 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0244. Min Act: -0.0003

Data Index: 474630 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0233. Min Act: -0.0003

Data Index: 651864 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0251. Min Act: -0.0003

Data Index: 230377 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0230. Min Act: -0.0003

Data Index: 254835 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0250. Min Act: -0.0003

Data Index: 936013 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0238. Min Act: -0.0003

Data Index: 255656 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0237. Min Act: -0.0003

Data Index: 312425 (C4 (Web Text))

Max Activating Token Index: 878