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

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

Neuron 3487 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: 0.8725. Min Range: -0.8725

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1211796 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7908. Min Act: -0.0000

Data Index: 875116 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7587. Min Act: -0.0000

Data Index: 357368 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7722. Min Act: -0.0000

Data Index: 471065 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7077. Min Act: -0.0000

Data Index: 129195 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7361. Min Act: -0.0000

Data Index: 978244 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1196246 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1275212 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7322. Min Act: -0.0000

Data Index: 607109 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6978. Min Act: -0.0000

Data Index: 310004 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1062458 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.7041. Min Act: -0.0000

Data Index: 515822 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6800. Min Act: -0.0000

Data Index: 681666 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6542. Min Act: -0.0000

Data Index: 934581 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6723. Min Act: -0.0000

Data Index: 789951 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6294. Min Act: -0.0000

Data Index: 847165 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6388. Min Act: -0.0000

Data Index: 421917 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1057523 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6322. Min Act: -0.0000

Data Index: 198344 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.8725. Min Range: -0.8725

Max Act: 0.6075. Min Act: -0.0000

Data Index: 89758 (C4 (Web Text))

Max Activating Token Index: 536