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

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

Neuron 3523 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0963. Min Act: -0.0002

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0667. Min Act: -0.0002

Data Index: 362684 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0664. Min Act: -0.0002

Data Index: 974421 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1050372 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0615. Min Act: -0.0002

Data Index: 353322 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0613. Min Act: -0.0002

Data Index: 364092 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1028172 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0586. Min Act: -0.0002

Data Index: 63953 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1171820 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1110765 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0564. Min Act: -0.0002

Data Index: 488850 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1021796 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1132633 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1212878 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0584. Min Act: -0.0002

Data Index: 757229 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0559. Min Act: -0.0002

Data Index: 285795 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0543. Min Act: -0.0002

Data Index: 168131 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0539. Min Act: -0.0002

Data Index: 668317 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0537. Min Act: -0.0002

Data Index: 346649 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.0963. Min Range: -0.0963

Max Act: 0.0536. Min Act: -0.0002

Data Index: 307473 (C4 (Web Text))

Max Activating Token Index: 711