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

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

Neuron 4020 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: 1.3634. Min Range: -1.3634

Max Act: 1.3537. Min Act: -0.0000

Data Index: 525822 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.3634. Min Act: -0.0000

Data Index: 471603 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.2440. Min Act: -0.0000

Data Index: 567314 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.1954. Min Act: -0.0000

Data Index: 898271 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.2169. Min Act: -0.0000

Data Index: 594967 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.1304. Min Act: -0.0000

Data Index: 995289 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.1351. Min Act: 0.0000

Data Index: 560017 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.0659. Min Act: -0.0000

Data Index: 769899 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.1030. Min Act: 0.0000

Data Index: 101286 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1275989 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.0942. Min Act: 0.0000

Data Index: 702884 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1084694 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.0301. Min Act: -0.0000

Data Index: 741988 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.0149. Min Act: -0.0000

Data Index: 908558 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1267373 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 1.3634. Min Range: -1.3634

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1617985 (Python Code)

Max Activating Token Index: 259

Text #16

Max Range: 1.3634. Min Range: -1.3634

Max Act: 1.0576. Min Act: 0.0000

Data Index: 791341 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.3634. Min Range: -1.3634

Max Act: 0.9295. Min Act: -0.0000

Data Index: 484821 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 1.3634. Min Range: -1.3634

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1251798 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 1.3634. Min Range: -1.3634

Max Act: 0.9704. Min Act: -0.0000

Data Index: 191374 (C4 (Web Text))

Max Activating Token Index: 898