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

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

Neuron 3438 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.9145. Min Act: -0.0000

Data Index: 1333410 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8467. Min Act: -0.0000

Data Index: 377669 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8010. Min Act: -0.0000

Data Index: 511013 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8147. Min Act: -0.0000

Data Index: 1335393 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8745. Min Act: -0.0000

Data Index: 559400 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8161. Min Act: -0.0000

Data Index: 789546 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8303. Min Act: 0.0000

Data Index: 635320 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7832. Min Act: -0.0000

Data Index: 194825 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7919. Min Act: -0.0000

Data Index: 430754 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7818. Min Act: -0.0000

Data Index: 1194635 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7805. Min Act: 0.0000

Data Index: 202300 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7551. Min Act: -0.0000

Data Index: 122176 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1240951 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7447. Min Act: -0.0000

Data Index: 964138 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7560. Min Act: -0.0000

Data Index: 319432 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7582. Min Act: -0.0000

Data Index: 117746 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1184557 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1236724 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1243104 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7171. Min Act: -0.0000

Data Index: 90093 (C4 (Web Text))

Max Activating Token Index: 861