Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2853 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5824. Min Act: -0.0001

Data Index: 309502 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5272. Min Act: -0.0000

Data Index: 30962 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4607. Min Act: -0.0001

Data Index: 1026323 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.5103. Min Act: -0.0000

Data Index: 285108 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4639. Min Act: -0.0001

Data Index: 397655 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4480. Min Act: -0.0001

Data Index: 509839 (C4 (Web Text))

Max Activating Token Index: 438

Text #6

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4609. Min Act: -0.0000

Data Index: 767840 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4628. Min Act: -0.0001

Data Index: 1124913 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4312. Min Act: -0.0000

Data Index: 697788 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4284. Min Act: -0.0000

Data Index: 509415 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4245. Min Act: -0.0000

Data Index: 392531 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4223. Min Act: -0.0001

Data Index: 809875 (C4 (Web Text))

Max Activating Token Index: 897

Text #12

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4217. Min Act: -0.0001

Data Index: 1303840 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4023. Min Act: -0.0000

Data Index: 1225296 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4086. Min Act: -0.0001

Data Index: 209513 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4342. Min Act: -0.0001

Data Index: 1255333 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.4041. Min Act: -0.0001

Data Index: 571831 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.3590. Min Act: -0.0001

Data Index: 75192 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.3664. Min Act: -0.0000

Data Index: 919923 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.5824. Min Range: -0.5824

Max Act: 0.3868. Min Act: -0.0000

Data Index: 602771 (C4 (Web Text))

Max Activating Token Index: 497