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

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

Neuron 1036 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.6567. Min Act: -0.0000

Data Index: 249126 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5633. Min Act: -0.0000

Data Index: 761557 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5399. Min Act: -0.0000

Data Index: 197207 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1015353 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5461. Min Act: -0.0000

Data Index: 331924 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5099. Min Act: -0.0000

Data Index: 889146 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5244. Min Act: -0.0000

Data Index: 592903 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4860. Min Act: -0.0000

Data Index: 907393 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5316. Min Act: -0.0000

Data Index: 566315 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5084. Min Act: -0.0000

Data Index: 557656 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1033858 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.5023. Min Act: -0.0000

Data Index: 914417 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4803. Min Act: -0.0000

Data Index: 257145 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4626. Min Act: -0.0000

Data Index: 61337 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1108473 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1043033 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4610. Min Act: -0.0000

Data Index: 285578 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1010501 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4572. Min Act: -0.0000

Data Index: 272547 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.6567. Min Range: -0.6567

Max Act: 0.4530. Min Act: -0.0000

Data Index: 89129 (C4 (Web Text))

Max Activating Token Index: 451