Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1449 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.8817. Min Act: -0.0004

Data Index: 189003 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5627. Min Act: -0.0004

Data Index: 674878 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5182. Min Act: -0.0004

Data Index: 574081 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5859. Min Act: -0.0004

Data Index: 66570 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5844. Min Act: -0.0004

Data Index: 1065224 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5330. Min Act: -0.0004

Data Index: 1346494 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5028. Min Act: -0.0004

Data Index: 771152 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5646. Min Act: -0.0004

Data Index: 1114434 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5941. Min Act: -0.0004

Data Index: 870871 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5873. Min Act: -0.0004

Data Index: 283329 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4554. Min Act: -0.0004

Data Index: 502529 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5872. Min Act: -0.0004

Data Index: 936138 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5334. Min Act: -0.0004

Data Index: 939818 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5437. Min Act: -0.0004

Data Index: 856344 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5266. Min Act: -0.0004

Data Index: 83203 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.4682. Min Act: -0.0004

Data Index: 214992 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5152. Min Act: -0.0004

Data Index: 85184 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.6027. Min Act: -0.0004

Data Index: 690403 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5638. Min Act: -0.0004

Data Index: 1031868 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 0.8817. Min Range: -0.8817

Max Act: 0.5588. Min Act: -0.0004

Data Index: 81536 (C4 (Web Text))

Max Activating Token Index: 930