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

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

Neuron 3806 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: 0.5082. Min Range: -0.5082

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1117041 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1023923 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4451. Min Act: -0.0000

Data Index: 7187 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4077. Min Act: -0.0000

Data Index: 999369 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4044. Min Act: -0.0000

Data Index: 613796 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1138364 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1013322 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3841. Min Act: -0.0000

Data Index: 506648 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3710. Min Act: -0.0000

Data Index: 575264 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1271013 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1266311 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3653. Min Act: -0.0000

Data Index: 267995 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3446. Min Act: -0.0000

Data Index: 96432 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3437. Min Act: -0.0000

Data Index: 202995 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3338. Min Act: -0.0000

Data Index: 879926 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3232. Min Act: -0.0000

Data Index: 737057 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3295. Min Act: -0.0000

Data Index: 846398 (C4 (Web Text))

Max Activating Token Index: 147

Text #17

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3296. Min Act: -0.0000

Data Index: 196290 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3257. Min Act: -0.0000

Data Index: 51629 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3178. Min Act: -0.0000

Data Index: 814263 (C4 (Web Text))

Max Activating Token Index: 223