Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 463 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.7048. Min Act: -0.0002

Data Index: 1421531 (Python Code)

Max Activating Token Index: 180

Text #1

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6366. Min Act: -0.0002

Data Index: 1150812 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5767. Min Act: -0.0002

Data Index: 364549 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6148. Min Act: -0.0002

Data Index: 1073668 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4134. Min Act: -0.0002

Data Index: 1333620 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6167. Min Act: -0.0002

Data Index: 612986 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5236. Min Act: -0.0002

Data Index: 335226 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5023. Min Act: -0.0002

Data Index: 630661 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4270. Min Act: -0.0002

Data Index: 586359 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5535. Min Act: -0.0002

Data Index: 499450 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4870. Min Act: -0.0002

Data Index: 638021 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5643. Min Act: -0.0002

Data Index: 548903 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5693. Min Act: -0.0002

Data Index: 663 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5014. Min Act: -0.0002

Data Index: 534091 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5352. Min Act: -0.0002

Data Index: 831427 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4201. Min Act: -0.0002

Data Index: 963012 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5139. Min Act: -0.0002

Data Index: 1061988 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5223. Min Act: -0.0002

Data Index: 91954 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4313. Min Act: -0.0002

Data Index: 1126213 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4934. Min Act: -0.0002

Data Index: 445641 (C4 (Web Text))

Max Activating Token Index: 392