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

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

Neuron 4550 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.2096. Min Act: -0.0002

Data Index: 840496 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.2207. Min Act: -0.0002

Data Index: 1079175 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.2025. Min Act: -0.0002

Data Index: 189446 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1809. Min Act: -0.0002

Data Index: 447327 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1876. Min Act: -0.0002

Data Index: 732095 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1870. Min Act: -0.0002

Data Index: 1059235 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1794. Min Act: -0.0002

Data Index: 566575 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1821. Min Act: -0.0002

Data Index: 355611 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1855. Min Act: -0.0002

Data Index: 351944 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1881. Min Act: -0.0002

Data Index: 335494 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1914. Min Act: -0.0002

Data Index: 775671 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1749. Min Act: -0.0002

Data Index: 554042 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1719. Min Act: -0.0002

Data Index: 591281 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1689. Min Act: -0.0002

Data Index: 792401 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1617. Min Act: -0.0002

Data Index: 352234 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1677. Min Act: -0.0002

Data Index: 17888 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1671. Min Act: -0.0002

Data Index: 661554 (C4 (Web Text))

Max Activating Token Index: 450

Text #17

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1637. Min Act: -0.0002

Data Index: 814545 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1691. Min Act: -0.0002

Data Index: 901608 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.2207. Min Range: -0.2207

Max Act: 0.1569. Min Act: -0.0002

Data Index: 551963 (C4 (Web Text))

Max Activating Token Index: 691