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

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

Neuron 1593 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9752. Min Act: -0.0000

Data Index: 989751 (C4 (Web Text))

Max Activating Token Index: 95

Text #1

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9389. Min Act: -0.0000

Data Index: 260024 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8276. Min Act: -0.0000

Data Index: 305660 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.9465. Min Act: -0.0000

Data Index: 53351 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8461. Min Act: -0.0000

Data Index: 906581 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8279. Min Act: -0.0000

Data Index: 422555 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.8339. Min Act: -0.0000

Data Index: 15669 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7799. Min Act: -0.0000

Data Index: 77842 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7880. Min Act: -0.0000

Data Index: 512735 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7780. Min Act: -0.0000

Data Index: 173130 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7104. Min Act: -0.0000

Data Index: 750954 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1064872 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7500. Min Act: -0.0000

Data Index: 195970 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7595. Min Act: -0.0000

Data Index: 1167193 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1235641 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7478. Min Act: -0.0000

Data Index: 921133 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7198. Min Act: -0.0000

Data Index: 924393 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7695. Min Act: -0.0000

Data Index: 244838 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7172. Min Act: -0.0000

Data Index: 206231 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.9752. Min Range: -0.9752

Max Act: 0.7186. Min Act: -0.0000

Data Index: 993099 (C4 (Web Text))

Max Activating Token Index: 258