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

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

Neuron 2090 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: 1.2133. Min Range: -1.2133

Max Act: 1.2133. Min Act: -0.0001

Data Index: 969574 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.1945. Min Act: -0.0001

Data Index: 732141 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.9446. Min Act: -0.0001

Data Index: 480653 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.8681. Min Act: -0.0001

Data Index: 940149 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.8918. Min Act: -0.0001

Data Index: 1173992 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.2133. Min Range: -1.2133

Max Act: 1.0374. Min Act: -0.0001

Data Index: 485298 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.9868. Min Act: -0.0001

Data Index: 1172082 (C4 (Web Text))

Max Activating Token Index: 706

Text #7

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.9982. Min Act: -0.0001

Data Index: 1069966 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.6991. Min Act: -0.0001

Data Index: 850858 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.8355. Min Act: -0.0001

Data Index: 89008 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.8334. Min Act: -0.0001

Data Index: 2566 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.8747. Min Act: -0.0001

Data Index: 638481 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.6610. Min Act: -0.0001

Data Index: 1058229 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.7586. Min Act: -0.0001

Data Index: 336506 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.9343. Min Act: -0.0001

Data Index: 516862 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.6856. Min Act: -0.0001

Data Index: 158119 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.7822. Min Act: -0.0001

Data Index: 458835 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.8836. Min Act: -0.0001

Data Index: 1283223 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.7524. Min Act: -0.0001

Data Index: 283133 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.2133. Min Range: -1.2133

Max Act: 0.7666. Min Act: -0.0001

Data Index: 1285046 (C4 (Web Text))

Max Activating Token Index: 625