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

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

Neuron 263 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: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0002

Data Index: 80048 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0594. Min Act: -0.0002

Data Index: 266927 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0541. Min Act: -0.0002

Data Index: 81099 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0540. Min Act: -0.0001

Data Index: 344762 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0545. Min Act: -0.0002

Data Index: 994689 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0516. Min Act: -0.0002

Data Index: 904886 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0497. Min Act: -0.0002

Data Index: 348737 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1258491 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0488. Min Act: -0.0002

Data Index: 347907 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0497. Min Act: -0.0002

Data Index: 314282 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0502. Min Act: -0.0001

Data Index: 373876 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0500. Min Act: -0.0002

Data Index: 120939 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0469. Min Act: -0.0002

Data Index: 1160297 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1314708 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0459. Min Act: -0.0002

Data Index: 13841 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0457. Min Act: -0.0001

Data Index: 34788 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1267719 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0434. Min Act: -0.0000

Data Index: 894040 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0433. Min Act: -0.0002

Data Index: 721187 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0439. Min Act: -0.0001

Data Index: 561272 (C4 (Web Text))

Max Activating Token Index: 381