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

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

Neuron 4679 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.4280. Min Act: -0.0000

Data Index: 10459 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3535. Min Act: -0.0000

Data Index: 752308 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3533. Min Act: -0.0000

Data Index: 854090 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3098. Min Act: -0.0000

Data Index: 70463 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3331. Min Act: -0.0000

Data Index: 8817 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3178. Min Act: -0.0000

Data Index: 168166 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3254. Min Act: -0.0000

Data Index: 119374 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3236. Min Act: -0.0000

Data Index: 51682 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2892. Min Act: -0.0000

Data Index: 677387 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3178. Min Act: -0.0000

Data Index: 326901 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3018. Min Act: -0.0000

Data Index: 135065 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1064371 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2934. Min Act: -0.0000

Data Index: 421807 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2831. Min Act: -0.0000

Data Index: 718379 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2897. Min Act: -0.0000

Data Index: 155181 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2720. Min Act: -0.0000

Data Index: 477899 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2790. Min Act: -0.0000

Data Index: 492752 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2681. Min Act: -0.0000

Data Index: 291367 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2621. Min Act: -0.0000

Data Index: 491556 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2783. Min Act: -0.0000

Data Index: 981050 (C4 (Web Text))

Max Activating Token Index: 635