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

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

Neuron 2578 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5294. Min Range: -3.5294

Max Act: 3.5294. Min Act: -0.0001

Data Index: 1259246 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.8274. Min Act: -0.0001

Data Index: 1009041 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.6968. Min Act: -0.0001

Data Index: 240463 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.6389. Min Act: -0.0001

Data Index: 221654 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.6191. Min Act: -0.0001

Data Index: 657371 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.5871. Min Act: -0.0001

Data Index: 324734 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.2627. Min Act: -0.0001

Data Index: 682571 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.4854. Min Act: -0.0000

Data Index: 1279540 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.4841. Min Act: -0.0001

Data Index: 1128770 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.4756. Min Act: -0.0001

Data Index: 1185023 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.7952. Min Act: -0.0001

Data Index: 182910 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.6455. Min Act: -0.0001

Data Index: 798689 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.4142. Min Act: -0.0001

Data Index: 1180294 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.1666. Min Act: -0.0001

Data Index: 344535 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.2470. Min Act: -0.0001

Data Index: 376531 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.5916. Min Act: -0.0000

Data Index: 1272848 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.2221. Min Act: -0.0001

Data Index: 452375 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.4519. Min Act: -0.0001

Data Index: 207462 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.4420. Min Act: -0.0001

Data Index: 578841 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 3.5294. Min Range: -3.5294

Max Act: 2.3365. Min Act: -0.0001

Data Index: 367049 (C4 (Web Text))

Max Activating Token Index: 75