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

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

Neuron 762 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.9207. Min Act: -0.0002

Data Index: 302960 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.7708. Min Act: -0.0002

Data Index: 750973 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.9207. Min Range: -1.9207

Max Act: 1.0070. Min Act: -0.0002

Data Index: 178416 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.9107. Min Act: -0.0002

Data Index: 262874 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.7737. Min Act: -0.0002

Data Index: 1060583 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.6686. Min Act: -0.0002

Data Index: 700006 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.7612. Min Act: -0.0002

Data Index: 540182 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.8802. Min Act: -0.0002

Data Index: 273995 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.5374. Min Act: -0.0002

Data Index: 960180 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.8305. Min Act: -0.0002

Data Index: 876062 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.6575. Min Act: -0.0002

Data Index: 641734 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.5786. Min Act: -0.0002

Data Index: 1277872 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.7657. Min Act: -0.0002

Data Index: 878108 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.6496. Min Act: -0.0002

Data Index: 832051 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.5729. Min Act: -0.0002

Data Index: 52079 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.5953. Min Act: -0.0002

Data Index: 1228296 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.7498. Min Act: -0.0002

Data Index: 398241 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.5670. Min Act: -0.0002

Data Index: 1316041 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.4308. Min Act: -0.0002

Data Index: 1005517 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 1.9207. Min Range: -1.9207

Max Act: 0.7070. Min Act: -0.0002

Data Index: 695980 (C4 (Web Text))

Max Activating Token Index: 260