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

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

Neuron 3199 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: 1.3072. Min Range: -1.3072

Max Act: 1.3072. Min Act: -0.0000

Data Index: 733285 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 1.3072. Min Range: -1.3072

Max Act: 1.0837. Min Act: -0.0000

Data Index: 774000 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 1.3072. Min Range: -1.3072

Max Act: 1.0017. Min Act: -0.0000

Data Index: 291421 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.9540. Min Act: -0.0000

Data Index: 615408 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.9056. Min Act: -0.0000

Data Index: 586439 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.8836. Min Act: -0.0000

Data Index: 160892 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.8121. Min Act: -0.0000

Data Index: 179474 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.8065. Min Act: -0.0000

Data Index: 923052 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1049554 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7969. Min Act: -0.0000

Data Index: 421090 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1008864 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1033442 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7573. Min Act: -0.0000

Data Index: 826264 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7540. Min Act: -0.0000

Data Index: 157758 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1218370 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7495. Min Act: -0.0000

Data Index: 341688 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7277. Min Act: -0.0000

Data Index: 329436 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1038213 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.8429. Min Act: -0.0000

Data Index: 361142 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 1.3072. Min Range: -1.3072

Max Act: 0.7354. Min Act: -0.0000

Data Index: 422051 (C4 (Web Text))

Max Activating Token Index: 983