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

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

Neuron 875 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: 0.6714. Min Range: -0.6714

Max Act: 0.6714. Min Act: -0.0000

Data Index: 708328 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1337875 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1229622 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5185. Min Act: -0.0000

Data Index: 573333 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5183. Min Act: -0.0000

Data Index: 652996 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4676. Min Act: -0.0000

Data Index: 840086 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5042. Min Act: -0.0000

Data Index: 572003 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4989. Min Act: -0.0000

Data Index: 521954 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4296. Min Act: -0.0000

Data Index: 71509 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4827. Min Act: -0.0000

Data Index: 928669 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1102061 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4472. Min Act: -0.0000

Data Index: 185444 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1322854 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1294662 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4093. Min Act: -0.0000

Data Index: 685348 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4484. Min Act: -0.0000

Data Index: 236526 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4428. Min Act: -0.0000

Data Index: 545993 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.3969. Min Act: -0.0000

Data Index: 821487 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4231. Min Act: -0.0000

Data Index: 290454 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1119278 (C4 (Web Text))

Max Activating Token Index: 82