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

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

Neuron 464 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: 1.1238. Min Range: -1.1238

Max Act: 1.1238. Min Act: -0.0000

Data Index: 904423 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9409. Min Act: -0.0000

Data Index: 581010 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9840. Min Act: -0.0000

Data Index: 286581 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9389. Min Act: -0.0000

Data Index: 1055374 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9084. Min Act: -0.0000

Data Index: 268568 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.9187. Min Act: -0.0000

Data Index: 815936 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1053671 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1273301 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8500. Min Act: -0.0000

Data Index: 396468 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8392. Min Act: -0.0000

Data Index: 802242 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8239. Min Act: -0.0000

Data Index: 303893 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1253507 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7972. Min Act: -0.0000

Data Index: 214853 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.8485. Min Act: -0.0000

Data Index: 986843 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7867. Min Act: -0.0000

Data Index: 977008 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7517. Min Act: -0.0000

Data Index: 568779 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7714. Min Act: -0.0000

Data Index: 62784 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1115954 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7621. Min Act: -0.0000

Data Index: 563405 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 1.1238. Min Range: -1.1238

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1156343 (C4 (Web Text))

Max Activating Token Index: 216