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

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

Neuron 1829 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: 0.7250. Min Range: -0.7250

Max Act: 0.7250. Min Act: -0.0001

Data Index: 691293 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5218. Min Act: -0.0001

Data Index: 42175 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5824. Min Act: -0.0000

Data Index: 716575 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5142. Min Act: -0.0001

Data Index: 179036 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4396. Min Act: -0.0001

Data Index: 175623 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5224. Min Act: -0.0001

Data Index: 1078217 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1224635 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3882. Min Act: -0.0001

Data Index: 1249086 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4278. Min Act: -0.0001

Data Index: 988283 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4893. Min Act: -0.0000

Data Index: 617808 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.4523. Min Act: -0.0001

Data Index: 828416 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3915. Min Act: -0.0000

Data Index: 624046 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3986. Min Act: -0.0000

Data Index: 158673 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1199199 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3541. Min Act: -0.0001

Data Index: 471328 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3484. Min Act: -0.0001

Data Index: 1257999 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3589. Min Act: -0.0000

Data Index: 429599 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3837. Min Act: -0.0001

Data Index: 854554 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3671. Min Act: -0.0000

Data Index: 907396 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.3360. Min Act: -0.0000

Data Index: 889366 (C4 (Web Text))

Max Activating Token Index: 941