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

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

Neuron 4623 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.3850. Min Act: -0.0000

Data Index: 1044568 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.3352. Min Act: -0.0000

Data Index: 37246 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.2388. Min Act: -0.0000

Data Index: 104375 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 1.3850. Min Range: -1.3850

Max Act: 1.0945. Min Act: -0.0000

Data Index: 910310 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9899. Min Act: -0.0000

Data Index: 604141 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9551. Min Act: -0.0000

Data Index: 169942 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1158278 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9228. Min Act: -0.0000

Data Index: 648061 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9672. Min Act: -0.0000

Data Index: 91990 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9680. Min Act: -0.0000

Data Index: 355510 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9355. Min Act: -0.0000

Data Index: 764074 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1191283 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9224. Min Act: -0.0000

Data Index: 1197502 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8347. Min Act: -0.0000

Data Index: 492488 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9541. Min Act: -0.0000

Data Index: 976198 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9383. Min Act: -0.0000

Data Index: 178066 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.7859. Min Act: -0.0000

Data Index: 788788 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8803. Min Act: -0.0000

Data Index: 542811 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1040271 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.3850. Min Range: -1.3850

Max Act: 0.8602. Min Act: -0.0000

Data Index: 796556 (C4 (Web Text))

Max Activating Token Index: 36