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

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

Neuron 3595 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1010682 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0389. Min Act: -0.0003

Data Index: 105896 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0367. Min Act: -0.0003

Data Index: 182477 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0400. Min Act: -0.0004

Data Index: 438802 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0378. Min Act: -0.0003

Data Index: 203211 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0321. Min Act: -0.0003

Data Index: 2879 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0337. Min Act: -0.0003

Data Index: 247676 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0328. Min Act: -0.0003

Data Index: 140592 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0320. Min Act: -0.0003

Data Index: 992307 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0311. Min Act: -0.0003

Data Index: 972777 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0309. Min Act: -0.0003

Data Index: 965742 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0328. Min Act: -0.0003

Data Index: 835684 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0336. Min Act: -0.0003

Data Index: 88777 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0324. Min Act: -0.0003

Data Index: 362971 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1008363 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0308. Min Act: -0.0003

Data Index: 310119 (C4 (Web Text))

Max Activating Token Index: 725

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0334. Min Act: -0.0003

Data Index: 181681 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1106091 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0307. Min Act: -0.0003

Data Index: 11154 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1027938 (C4 (Web Text))

Max Activating Token Index: 253