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

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

Neuron 2297 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.6887. Min Act: -0.0000

Data Index: 283564 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.6446. Min Act: -0.0000

Data Index: 645516 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.4488. Min Act: -0.0000

Data Index: 1319424 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.4433. Min Act: -0.0000

Data Index: 183299 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.4321. Min Act: -0.0000

Data Index: 388055 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.4052. Min Act: -0.0000

Data Index: 72272 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1263671 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.4230. Min Act: 0.0000

Data Index: 182057 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.4133. Min Act: -0.0000

Data Index: 587389 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1074747 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3991. Min Act: -0.0000

Data Index: 752453 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3838. Min Act: -0.0000

Data Index: 412527 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1107084 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1201172 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3795. Min Act: -0.0000

Data Index: 206137 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3797. Min Act: -0.0000

Data Index: 108651 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3614. Min Act: -0.0000

Data Index: 279567 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3671. Min Act: -0.0000

Data Index: 395348 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3772. Min Act: -0.0000

Data Index: 930232 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.6887. Min Range: -0.6887

Max Act: 0.3657. Min Act: -0.0000

Data Index: 717157 (C4 (Web Text))

Max Activating Token Index: 113