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

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

Neuron 95 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.8948. Min Act: -0.0000

Data Index: 287681 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.8332. Min Act: -0.0000

Data Index: 500929 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.8196. Min Act: -0.0000

Data Index: 805740 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7979. Min Act: -0.0000

Data Index: 42697 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7642. Min Act: -0.0000

Data Index: 100428 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7467. Min Act: -0.0000

Data Index: 492684 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7353. Min Act: -0.0000

Data Index: 460436 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7516. Min Act: -0.0000

Data Index: 1357637 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7307. Min Act: -0.0000

Data Index: 671727 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7222. Min Act: -0.0000

Data Index: 883060 (C4 (Web Text))

Max Activating Token Index: 530

Text #10

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7084. Min Act: -0.0000

Data Index: 415693 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7246. Min Act: -0.0000

Data Index: 102779 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7037. Min Act: 0.0000

Data Index: 406153 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.7012. Min Act: -0.0000

Data Index: 879866 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6485. Min Act: -0.0000

Data Index: 472734 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6647. Min Act: -0.0000

Data Index: 193516 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6667. Min Act: -0.0000

Data Index: 394071 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6651. Min Act: -0.0000

Data Index: 595563 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6590. Min Act: -0.0000

Data Index: 782416 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.8948. Min Range: -0.8948

Max Act: 0.6826. Min Act: -0.0000

Data Index: 651436 (C4 (Web Text))

Max Activating Token Index: 797