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

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

Neuron 3671 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.3220. Min Act: -0.0000

Data Index: 20778 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2991. Min Act: -0.0000

Data Index: 409937 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2981. Min Act: -0.0000

Data Index: 1009299 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2827. Min Act: -0.0000

Data Index: 612922 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1144224 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2592. Min Act: -0.0000

Data Index: 659434 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2572. Min Act: -0.0000

Data Index: 387182 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2483. Min Act: -0.0000

Data Index: 1243326 (C4 (Web Text))

Max Activating Token Index: 637

Text #8

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2352. Min Act: -0.0000

Data Index: 535843 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2299. Min Act: -0.0000

Data Index: 285426 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2361. Min Act: -0.0000

Data Index: 123491 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2416. Min Act: -0.0000

Data Index: 455209 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2364. Min Act: -0.0000

Data Index: 341465 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1012381 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2345. Min Act: -0.0000

Data Index: 222576 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2329. Min Act: -0.0000

Data Index: 943343 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2166. Min Act: -0.0000

Data Index: 922731 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2291. Min Act: -0.0000

Data Index: 997611 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2284. Min Act: -0.0000

Data Index: 921434 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.3220. Min Range: -0.3220

Max Act: 0.2348. Min Act: -0.0000

Data Index: 195279 (C4 (Web Text))

Max Activating Token Index: 971