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

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

Neuron 4028 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.5292. Min Act: -0.0000

Data Index: 14555 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4711. Min Act: -0.0000

Data Index: 477415 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1302714 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4070. Min Act: -0.0000

Data Index: 401453 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4323. Min Act: -0.0000

Data Index: 842345 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4012. Min Act: -0.0000

Data Index: 1129309 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1188200 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1326273 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.4168. Min Act: -0.0000

Data Index: 703876 (C4 (Web Text))

Max Activating Token Index: 803

Text #9

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3937. Min Act: -0.0000

Data Index: 810927 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3811. Min Act: -0.0000

Data Index: 186554 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1158427 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3671. Min Act: -0.0000

Data Index: 788880 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1122840 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1039395 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3080. Min Act: -0.0000

Data Index: 301085 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3333. Min Act: -0.0000

Data Index: 735031 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1272055 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.3092. Min Act: -0.0000

Data Index: 797136 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.5292. Min Range: -0.5292

Max Act: 0.2909. Min Act: -0.0000

Data Index: 173000 (C4 (Web Text))

Max Activating Token Index: 350