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

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

Neuron 1117 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2862. Min Act: -0.0000

Data Index: 826464 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1204789 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2714. Min Act: -0.0000

Data Index: 872132 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2641. Min Act: -0.0000

Data Index: 716779 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2473. Min Act: -0.0000

Data Index: 715034 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2459. Min Act: -0.0000

Data Index: 110989 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1021022 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2408. Min Act: -0.0000

Data Index: 336090 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2231. Min Act: -0.0000

Data Index: 80520 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2218. Min Act: -0.0000

Data Index: 848457 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2210. Min Act: -0.0000

Data Index: 356168 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2264. Min Act: -0.0000

Data Index: 174717 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2173. Min Act: -0.0000

Data Index: 202861 (C4 (Web Text))

Max Activating Token Index: 202

Text #13

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2242. Min Act: -0.0000

Data Index: 988582 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2147. Min Act: -0.0000

Data Index: 26925 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2226. Min Act: -0.0000

Data Index: 811277 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2127. Min Act: -0.0000

Data Index: 762768 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2275. Min Act: -0.0000

Data Index: 678630 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.2115. Min Act: -0.0000

Data Index: 201012 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.2862. Min Range: -0.2862

Max Act: 0.1996. Min Act: -0.0000

Data Index: 655703 (C4 (Web Text))

Max Activating Token Index: 375