Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 888 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0000

Data Index: 1029523 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0282. Min Act: -0.0000

Data Index: 366444 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1619508 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1184602 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0229. Min Act: -0.0001

Data Index: 714129 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0238. Min Act: -0.0001

Data Index: 998747 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0237. Min Act: -0.0001

Data Index: 596662 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0235. Min Act: -0.0000

Data Index: 914840 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1474687 (Python Code)

Max Activating Token Index: 1011

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0207. Min Act: -0.0001

Data Index: 872970 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0233. Min Act: -0.0000

Data Index: 913231 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1268266 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1209520 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0235. Min Act: -0.0001

Data Index: 169559 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0223. Min Act: -0.0001

Data Index: 385145 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1512759 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0221. Min Act: -0.0001

Data Index: 675139 (C4 (Web Text))

Max Activating Token Index: 985

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0200. Min Act: -0.0001

Data Index: 379710 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0220. Min Act: -0.0001

Data Index: 1435299 (Python Code)

Max Activating Token Index: 766