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

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

Neuron 577 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.5195. Min Act: -0.0001

Data Index: 769801 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.5212. Min Act: -0.0001

Data Index: 666794 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.5030. Min Act: -0.0001

Data Index: 149136 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4630. Min Act: -0.0001

Data Index: 1111404 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4443. Min Act: -0.0001

Data Index: 412511 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4332. Min Act: -0.0000

Data Index: 477785 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4495. Min Act: -0.0000

Data Index: 191932 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4291. Min Act: -0.0000

Data Index: 536263 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1103947 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4310. Min Act: -0.0000

Data Index: 76586 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4431. Min Act: -0.0001

Data Index: 695696 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4523. Min Act: -0.0001

Data Index: 535408 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4205. Min Act: -0.0000

Data Index: 177103 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4465. Min Act: -0.0001

Data Index: 1062821 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4088. Min Act: -0.0001

Data Index: 1132511 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3862. Min Act: -0.0000

Data Index: 307214 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.4007. Min Act: -0.0000

Data Index: 198645 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3850. Min Act: -0.0001

Data Index: 1184331 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3826. Min Act: -0.0000

Data Index: 206349 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.5212. Min Range: -0.5212

Max Act: 0.3935. Min Act: -0.0001

Data Index: 289930 (C4 (Web Text))

Max Activating Token Index: 1015