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

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

Neuron 3689 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1191942 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3658. Min Act: -0.0000

Data Index: 676041 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3087. Min Act: -0.0000

Data Index: 193944 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3076. Min Act: -0.0000

Data Index: 120601 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2830. Min Act: -0.0000

Data Index: 468645 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1336422 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2819. Min Act: -0.0000

Data Index: 58979 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2787. Min Act: -0.0000

Data Index: 501100 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2623. Min Act: -0.0000

Data Index: 873265 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2730. Min Act: -0.0000

Data Index: 65080 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1069243 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2615. Min Act: -0.0000

Data Index: 593794 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1255327 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2590. Min Act: -0.0000

Data Index: 567898 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1261086 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2586. Min Act: -0.0000

Data Index: 1230091 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2517. Min Act: -0.0000

Data Index: 843096 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1331279 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2389. Min Act: -0.0000

Data Index: 411181 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2491. Min Act: -0.0000

Data Index: 734865 (C4 (Web Text))

Max Activating Token Index: 513