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

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

Neuron 2918 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4444. Min Act: -0.0001

Data Index: 384667 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4590. Min Act: -0.0001

Data Index: 335194 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4361. Min Act: -0.0001

Data Index: 848565 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4361. Min Act: -0.0001

Data Index: 885262 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4513. Min Act: -0.0001

Data Index: 1016596 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4396. Min Act: -0.0001

Data Index: 1342527 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4393. Min Act: -0.0001

Data Index: 394943 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4358. Min Act: -0.0001

Data Index: 646967 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4169. Min Act: -0.0001

Data Index: 936383 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4273. Min Act: -0.0001

Data Index: 1010602 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4082. Min Act: -0.0001

Data Index: 1067055 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4138. Min Act: -0.0001

Data Index: 512578 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4279. Min Act: -0.0001

Data Index: 412384 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4381. Min Act: -0.0001

Data Index: 577991 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4228. Min Act: -0.0001

Data Index: 934818 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4086. Min Act: -0.0001

Data Index: 1129898 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4021. Min Act: -0.0001

Data Index: 682823 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4208. Min Act: -0.0001

Data Index: 1229527 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4190. Min Act: -0.0001

Data Index: 436096 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4328. Min Act: -0.0001

Data Index: 1247697 (C4 (Web Text))

Max Activating Token Index: 6