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

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

Neuron 2650 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: 1.7165. Min Range: -1.7165

Max Act: 1.7165. Min Act: -0.0000

Data Index: 494300 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.5614. Min Act: -0.0000

Data Index: 260393 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.5024. Min Act: -0.0000

Data Index: 205846 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1332794 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4591. Min Act: -0.0000

Data Index: 11101 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4661. Min Act: -0.0000

Data Index: 592600 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4546. Min Act: -0.0000

Data Index: 26573 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.5693. Min Act: -0.0000

Data Index: 471435 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.5208. Min Act: -0.0000

Data Index: 985421 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4438. Min Act: -0.0000

Data Index: 392290 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4883. Min Act: -0.0000

Data Index: 1326004 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1117319 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1313756 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4364. Min Act: -0.0000

Data Index: 521557 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1331940 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1061514 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.3926. Min Act: -0.0000

Data Index: 597771 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4062. Min Act: -0.0000

Data Index: 140590 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.4467. Min Act: -0.0000

Data Index: 707196 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 1.7165. Min Range: -1.7165

Max Act: 1.2508. Min Act: -0.0000

Data Index: 273538 (C4 (Web Text))

Max Activating Token Index: 720