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

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

Neuron 3028 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.1562. Min Act: -0.0000

Data Index: 655655 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0897. Min Act: -0.0000

Data Index: 888127 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0948. Min Act: -0.0000

Data Index: 677839 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9893. Min Act: -0.0000

Data Index: 17775 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9297. Min Act: -0.0000

Data Index: 693464 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9300. Min Act: -0.0000

Data Index: 548936 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9811. Min Act: -0.0000

Data Index: 357254 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1128932 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9634. Min Act: -0.0000

Data Index: 986205 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9500. Min Act: -0.0000

Data Index: 985342 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9397. Min Act: -0.0000

Data Index: 389374 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1143054 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 1.1562. Min Range: -1.1562

Max Act: 1.0001. Min Act: -0.0000

Data Index: 908623 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1322142 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9313. Min Act: -0.0000

Data Index: 270547 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9190. Min Act: -0.0000

Data Index: 674336 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9058. Min Act: -0.0000

Data Index: 1228 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9099. Min Act: 0.0000

Data Index: 567914 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.8991. Min Act: -0.0000

Data Index: 795801 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.1562. Min Range: -1.1562

Max Act: 0.9008. Min Act: -0.0000

Data Index: 1067580 (C4 (Web Text))

Max Activating Token Index: 61