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

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

Neuron 2220 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3316. Min Range: -1.3316

Max Act: 1.3316. Min Act: -0.0000

Data Index: 690226 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 1.3316. Min Range: -1.3316

Max Act: 1.2656. Min Act: 0.0000

Data Index: 1295668 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.3316. Min Range: -1.3316

Max Act: 1.1789. Min Act: -0.0000

Data Index: 38661 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.9932. Min Act: -0.0000

Data Index: 819083 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 1.3316. Min Range: -1.3316

Max Act: 1.0239. Min Act: -0.0000

Data Index: 908351 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 1.3316. Min Range: -1.3316

Max Act: 1.0250. Min Act: 0.0000

Data Index: 934537 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.9431. Min Act: -0.0000

Data Index: 575546 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.9346. Min Act: -0.0000

Data Index: 457318 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.9630. Min Act: 0.0000

Data Index: 426474 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.9356. Min Act: 0.0000

Data Index: 333135 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.9268. Min Act: -0.0000

Data Index: 1171833 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 1.3316. Min Range: -1.3316

Max Act: 1.0497. Min Act: -0.0000

Data Index: 924619 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.9322. Min Act: -0.0000

Data Index: 204827 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.9320. Min Act: -0.0000

Data Index: 212214 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.8257. Min Act: -0.0000

Data Index: 498317 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.8897. Min Act: 0.0000

Data Index: 287689 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1071278 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.8183. Min Act: 0.0000

Data Index: 481187 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.8235. Min Act: 0.0000

Data Index: 904335 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.3316. Min Range: -1.3316

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1056553 (C4 (Web Text))

Max Activating Token Index: 841