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

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

Neuron 4479 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.5566. Min Act: -0.0000

Data Index: 1122373 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.4220. Min Act: -0.0000

Data Index: 514061 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.4462. Min Act: -0.0000

Data Index: 911693 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.3654. Min Act: -0.0000

Data Index: 667488 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.3056. Min Act: -0.0000

Data Index: 289778 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.1687. Min Act: -0.0000

Data Index: 991701 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.2657. Min Act: -0.0000

Data Index: 1039527 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.1929. Min Act: -0.0000

Data Index: 521560 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.2152. Min Act: -0.0000

Data Index: 1035723 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.0998. Min Act: -0.0000

Data Index: 1143476 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.5566. Min Range: -1.5566

Max Act: 0.9784. Min Act: -0.0000

Data Index: 915212 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.0783. Min Act: -0.0000

Data Index: 820232 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.1317. Min Act: -0.0000

Data Index: 919249 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.0774. Min Act: -0.0000

Data Index: 281413 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.1602. Min Act: -0.0000

Data Index: 479868 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.1150. Min Act: -0.0000

Data Index: 797415 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.5566. Min Range: -1.5566

Max Act: 0.9954. Min Act: -0.0000

Data Index: 43858 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.0752. Min Act: -0.0000

Data Index: 733903 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.0503. Min Act: -0.0000

Data Index: 960092 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 1.5566. Min Range: -1.5566

Max Act: 1.0147. Min Act: -0.0000

Data Index: 667655 (C4 (Web Text))

Max Activating Token Index: 972