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

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

Neuron 4438 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.9914. Min Act: -0.0000

Data Index: 485632 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 1.0679. Min Range: -1.0679

Max Act: 1.0679. Min Act: -0.0000

Data Index: 917542 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7987. Min Act: -0.0000

Data Index: 72969 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.8049. Min Act: -0.0000

Data Index: 387801 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7011. Min Act: -0.0000

Data Index: 529731 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.8179. Min Act: -0.0000

Data Index: 257404 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7901. Min Act: -0.0000

Data Index: 184544 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7496. Min Act: -0.0000

Data Index: 625729 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1274118 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7105. Min Act: -0.0000

Data Index: 264182 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1241581 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7402. Min Act: -0.0000

Data Index: 800566 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.8284. Min Act: -0.0000

Data Index: 82984 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7002. Min Act: -0.0000

Data Index: 939229 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1162737 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7406. Min Act: -0.0000

Data Index: 36471 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7359. Min Act: -0.0000

Data Index: 727175 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1341624 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.0679. Min Range: -1.0679

Max Act: 0.5970. Min Act: -0.0000

Data Index: 292149 (C4 (Web Text))

Max Activating Token Index: 714