Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 588 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.8484. Min Act: -0.0000

Data Index: 26544 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.7559. Min Act: -0.0000

Data Index: 565293 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.7045. Min Act: -0.0000

Data Index: 636384 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6790. Min Act: -0.0000

Data Index: 562783 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.7463. Min Act: -0.0000

Data Index: 324470 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6781. Min Act: -0.0000

Data Index: 686582 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.7302. Min Act: -0.0000

Data Index: 942371 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1050683 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1172882 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6807. Min Act: -0.0000

Data Index: 961092 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6514. Min Act: -0.0000

Data Index: 963207 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6748. Min Act: -0.0000

Data Index: 865411 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.5053. Min Act: -0.0000

Data Index: 701002 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6054. Min Act: -0.0000

Data Index: 455927 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6404. Min Act: -0.0000

Data Index: 31388 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.8096. Min Act: -0.0000

Data Index: 267370 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1257522 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6262. Min Act: -0.0000

Data Index: 542429 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1356106 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 0.8484. Min Range: -0.8484

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1001592 (C4 (Web Text))

Max Activating Token Index: 779