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

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

Neuron 2891 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.5879. Min Act: -0.0002

Data Index: 1263094 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.6067. Min Act: -0.0002

Data Index: 999193 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.2953. Min Act: -0.0003

Data Index: 1332131 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 1.6067. Min Range: -1.6067

Max Act: 1.1811. Min Act: -0.0003

Data Index: 446868 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.8747. Min Act: -0.0003

Data Index: 1179724 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6829. Min Act: -0.0003

Data Index: 1060595 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6710. Min Act: -0.0003

Data Index: 412865 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6841. Min Act: -0.0003

Data Index: 1090757 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6522. Min Act: -0.0003

Data Index: 835398 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6617. Min Act: -0.0003

Data Index: 870586 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6413. Min Act: -0.0003

Data Index: 1320615 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6370. Min Act: -0.0003

Data Index: 836370 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6356. Min Act: -0.0003

Data Index: 971348 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6338. Min Act: -0.0003

Data Index: 284755 (C4 (Web Text))

Max Activating Token Index: 379

Text #14

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6099. Min Act: -0.0003

Data Index: 1240360 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6470. Min Act: -0.0003

Data Index: 657389 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6059. Min Act: -0.0003

Data Index: 999374 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6331. Min Act: -0.0003

Data Index: 1211130 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6133. Min Act: -0.0003

Data Index: 502664 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.6067. Min Range: -1.6067

Max Act: 0.6247. Min Act: -0.0003

Data Index: 174311 (C4 (Web Text))

Max Activating Token Index: 981