Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 489 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1180. Min Act: -0.0001

Data Index: 420743 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1279608 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0807. Min Act: -0.0001

Data Index: 789436 (C4 (Web Text))

Max Activating Token Index: 713

Text #3

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0814. Min Act: -0.0001

Data Index: 330554 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0814. Min Act: -0.0001

Data Index: 934156 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0815. Min Act: -0.0001

Data Index: 474379 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0755. Min Act: -0.0001

Data Index: 1003451 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0782. Min Act: -0.0001

Data Index: 67039 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0772. Min Act: -0.0001

Data Index: 1197477 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0770. Min Act: -0.0001

Data Index: 467296 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0830. Min Act: -0.0001

Data Index: 502419 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0759. Min Act: -0.0001

Data Index: 647866 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0758. Min Act: -0.0001

Data Index: 998308 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0742. Min Act: -0.0001

Data Index: 680012 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0745. Min Act: -0.0001

Data Index: 18491 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0708. Min Act: -0.0001

Data Index: 483112 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1161039 (C4 (Web Text))

Max Activating Token Index: 311

Text #17

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1021926 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1050331 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0687. Min Act: -0.0001

Data Index: 963602 (C4 (Web Text))

Max Activating Token Index: 656