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

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

Neuron 2940 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8938. Min Act: -0.0000

Data Index: 466182 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.9729. Min Act: -0.0000

Data Index: 454539 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8838. Min Act: -0.0000

Data Index: 610616 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8327. Min Act: -0.0000

Data Index: 918670 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1278846 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8074. Min Act: -0.0000

Data Index: 267242 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8210. Min Act: -0.0000

Data Index: 367407 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8090. Min Act: -0.0000

Data Index: 1212280 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8066. Min Act: -0.0000

Data Index: 182090 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7548. Min Act: -0.0000

Data Index: 405423 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8011. Min Act: -0.0000

Data Index: 977672 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1315000 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1210579 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.8005. Min Act: -0.0000

Data Index: 1107936 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7970. Min Act: -0.0000

Data Index: 499556 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7389. Min Act: -0.0000

Data Index: 476489 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7580. Min Act: -0.0000

Data Index: 102834 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7620. Min Act: -0.0000

Data Index: 913814 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7856. Min Act: -0.0000

Data Index: 886541 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.9729. Min Range: -0.9729

Max Act: 0.7527. Min Act: -0.0000

Data Index: 868278 (C4 (Web Text))

Max Activating Token Index: 432