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

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

Neuron 3826 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.4759. Min Act: -0.0000

Data Index: 1031475 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.3863. Min Act: -0.0000

Data Index: 1260114 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2988. Min Act: -0.0000

Data Index: 1116784 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2783. Min Act: -0.0000

Data Index: 207200 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2501. Min Act: -0.0000

Data Index: 126155 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2695. Min Act: -0.0000

Data Index: 883557 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2158. Min Act: -0.0000

Data Index: 273450 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.1427. Min Act: -0.0000

Data Index: 220082 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0978. Min Act: -0.0000

Data Index: 937748 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0714. Min Act: -0.0000

Data Index: 824239 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0502. Min Act: -0.0000

Data Index: 607205 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0425. Min Act: -0.0000

Data Index: 973102 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 1.4759. Min Range: -1.4759

Max Act: 0.9089. Min Act: -0.0000

Data Index: 241905 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0700. Min Act: -0.0000

Data Index: 201969 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 1.4759. Min Range: -1.4759

Max Act: 0.9153. Min Act: -0.0000

Data Index: 47213 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 1.4759. Min Range: -1.4759

Max Act: 0.9069. Min Act: -0.0000

Data Index: 430047 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.4759. Min Range: -1.4759

Max Act: 0.9604. Min Act: -0.0000

Data Index: 697529 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.4759. Min Range: -1.4759

Max Act: 0.8938. Min Act: -0.0000

Data Index: 273999 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.4759. Min Range: -1.4759

Max Act: 0.8751. Min Act: -0.0000

Data Index: 708862 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.4759. Min Range: -1.4759

Max Act: 0.8607. Min Act: -0.0000

Data Index: 852479 (C4 (Web Text))

Max Activating Token Index: 665