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

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

Neuron 3756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.7256. Min Act: -0.0000

Data Index: 1003705 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4828. Min Act: -0.0000

Data Index: 210777 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4699. Min Act: -0.0000

Data Index: 517007 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3782. Min Act: -0.0000

Data Index: 75199 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4072. Min Act: -0.0000

Data Index: 312295 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3894. Min Act: -0.0000

Data Index: 75190 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3052. Min Act: -0.0000

Data Index: 365910 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.4029. Min Act: -0.0000

Data Index: 902837 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3871. Min Act: -0.0000

Data Index: 1334404 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.2349. Min Act: -0.0000

Data Index: 815703 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3028. Min Act: -0.0000

Data Index: 174151 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.3595. Min Act: -0.0000

Data Index: 1139986 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.2367. Min Act: -0.0000

Data Index: 1315491 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.2983. Min Act: -0.0000

Data Index: 1044014 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.2489. Min Act: -0.0000

Data Index: 402859 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1097175 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.1471. Min Act: -0.0000

Data Index: 466080 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.2001. Min Act: -0.0000

Data Index: 482370 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.1444. Min Act: -0.0000

Data Index: 443558 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.7256. Min Range: -1.7256

Max Act: 1.1967. Min Act: -0.0000

Data Index: 740439 (C4 (Web Text))

Max Activating Token Index: 131