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

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

Neuron 1745 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: 0.7128. Min Range: -0.7128

Max Act: 0.7128. Min Act: -0.0002

Data Index: 1528475 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6978. Min Act: -0.0002

Data Index: 813281 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6141. Min Act: -0.0002

Data Index: 345420 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6299. Min Act: -0.0002

Data Index: 836429 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6274. Min Act: -0.0002

Data Index: 1308835 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6289. Min Act: -0.0002

Data Index: 242323 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5977. Min Act: -0.0002

Data Index: 15769 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5987. Min Act: -0.0002

Data Index: 741222 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6085. Min Act: -0.0002

Data Index: 973946 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5784. Min Act: -0.0002

Data Index: 813384 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5497. Min Act: -0.0002

Data Index: 278775 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5530. Min Act: -0.0002

Data Index: 1186939 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5896. Min Act: -0.0002

Data Index: 76213 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5649. Min Act: -0.0002

Data Index: 1105419 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.6021. Min Act: -0.0002

Data Index: 549354 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5630. Min Act: -0.0002

Data Index: 723120 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5758. Min Act: -0.0002

Data Index: 514848 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5587. Min Act: -0.0002

Data Index: 216358 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5337. Min Act: -0.0002

Data Index: 268210 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.7128. Min Range: -0.7128

Max Act: 0.5328. Min Act: -0.0002

Data Index: 1395196 (Python Code)

Max Activating Token Index: 567