Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 462 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.2399. Min Act: -0.0001

Data Index: 1054184 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.2076. Min Act: -0.0002

Data Index: 837280 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.2075. Min Act: -0.0002

Data Index: 1154265 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1845. Min Act: -0.0002

Data Index: 384430 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.2009. Min Act: -0.0002

Data Index: 192267 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1780. Min Act: -0.0002

Data Index: 776120 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1125039 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1750. Min Act: -0.0002

Data Index: 564043 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1675. Min Act: -0.0001

Data Index: 926923 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1660. Min Act: -0.0001

Data Index: 187121 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1692. Min Act: -0.0002

Data Index: 180931 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1662. Min Act: -0.0002

Data Index: 1065089 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1673. Min Act: -0.0002

Data Index: 938992 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1730. Min Act: -0.0001

Data Index: 189189 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1642. Min Act: -0.0002

Data Index: 1011924 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1628. Min Act: -0.0002

Data Index: 253275 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1679. Min Act: -0.0001

Data Index: 732051 (C4 (Web Text))

Max Activating Token Index: 516

Text #17

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1607. Min Act: -0.0001

Data Index: 949184 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1513. Min Act: -0.0001

Data Index: 592481 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.2399. Min Range: -0.2399

Max Act: 0.1537. Min Act: -0.0002

Data Index: 101540 (C4 (Web Text))

Max Activating Token Index: 847