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

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

Neuron 29 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.2767. Min Act: -0.0001

Data Index: 672664 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.2031. Min Act: -0.0001

Data Index: 904893 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0420. Min Act: -0.0001

Data Index: 749794 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.1057. Min Act: -0.0001

Data Index: 1227670 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0258. Min Act: -0.0001

Data Index: 213688 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0535. Min Act: -0.0001

Data Index: 1199571 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0386. Min Act: -0.0001

Data Index: 720412 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0108. Min Act: -0.0001

Data Index: 407585 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9336. Min Act: -0.0001

Data Index: 510949 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0198. Min Act: -0.0001

Data Index: 1257424 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9389. Min Act: -0.0001

Data Index: 541744 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9903. Min Act: -0.0001

Data Index: 1129326 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0279. Min Act: -0.0001

Data Index: 1332651 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9805. Min Act: -0.0001

Data Index: 666586 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0151. Min Act: -0.0001

Data Index: 1322560 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9545. Min Act: -0.0001

Data Index: 16936 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9049. Min Act: -0.0001

Data Index: 599888 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9624. Min Act: -0.0001

Data Index: 868285 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9675. Min Act: -0.0001

Data Index: 492363 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9038. Min Act: -0.0001

Data Index: 404230 (C4 (Web Text))

Max Activating Token Index: 91