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

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

Neuron 5268 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0187. Min Range: -5.0187

Max Act: 5.0187. Min Act: -0.0000

Data Index: 716134 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 5.0187. Min Range: -5.0187

Max Act: 4.3084. Min Act: -0.0000

Data Index: 432866 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 5.0187. Min Range: -5.0187

Max Act: 4.1189. Min Act: -0.0000

Data Index: 1233044 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 5.0187. Min Range: -5.0187

Max Act: 4.1499. Min Act: -0.0000

Data Index: 897396 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.6910. Min Act: -0.0000

Data Index: 1035625 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.6555. Min Act: -0.0000

Data Index: 790316 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.4159. Min Act: -0.0000

Data Index: 997785 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.8360. Min Act: -0.0000

Data Index: 975641 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.4928. Min Act: -0.0000

Data Index: 1330326 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.4868. Min Act: -0.0000

Data Index: 1222535 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.6030. Min Act: -0.0000

Data Index: 1173614 (C4 (Web Text))

Max Activating Token Index: 928

Text #11

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.3261. Min Act: -0.0000

Data Index: 198293 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.3415. Min Act: -0.0000

Data Index: 728380 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.1075. Min Act: -0.0000

Data Index: 1335573 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.2102. Min Act: -0.0000

Data Index: 1002604 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 5.0187. Min Range: -5.0187

Max Act: 3.0989. Min Act: -0.0000

Data Index: 465239 (C4 (Web Text))

Max Activating Token Index: 777

Text #16

Max Range: 5.0187. Min Range: -5.0187

Max Act: 2.7847. Min Act: -0.0000

Data Index: 1188227 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 5.0187. Min Range: -5.0187

Max Act: 2.9274. Min Act: -0.0000

Data Index: 1249795 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 5.0187. Min Range: -5.0187

Max Act: 2.6977. Min Act: -0.0000

Data Index: 1151495 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 5.0187. Min Range: -5.0187

Max Act: 2.6355. Min Act: -0.0000

Data Index: 246927 (C4 (Web Text))

Max Activating Token Index: 478