Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3057 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4850. Min Act: -0.0001

Data Index: 1314745 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1282919 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4787. Min Act: -0.0001

Data Index: 622958 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4918. Min Act: -0.0001

Data Index: 915253 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4672. Min Act: -0.0001

Data Index: 279523 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4749. Min Act: -0.0001

Data Index: 897130 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4314. Min Act: -0.0001

Data Index: 270504 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4517. Min Act: -0.0001

Data Index: 370902 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4755. Min Act: -0.0001

Data Index: 753164 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1356482 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4554. Min Act: -0.0000

Data Index: 43357 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4683. Min Act: -0.0001

Data Index: 92139 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3972. Min Act: -0.0001

Data Index: 442294 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4116. Min Act: -0.0001

Data Index: 1109823 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4393. Min Act: -0.0001

Data Index: 944835 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4075. Min Act: -0.0001

Data Index: 673913 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3925. Min Act: -0.0001

Data Index: 429714 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4007. Min Act: -0.0001

Data Index: 316537 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3958. Min Act: -0.0001

Data Index: 6089 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4356. Min Act: -0.0001

Data Index: 74422 (C4 (Web Text))

Max Activating Token Index: 952