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

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

Neuron 589 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: 0.2766. Min Range: -0.2766

Max Act: 0.2748. Min Act: -0.0002

Data Index: 33823 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2651. Min Act: -0.0002

Data Index: 308297 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2624. Min Act: -0.0002

Data Index: 1104408 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2709. Min Act: -0.0002

Data Index: 806505 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2766. Min Act: -0.0002

Data Index: 491734 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2497. Min Act: -0.0002

Data Index: 127079 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2587. Min Act: -0.0002

Data Index: 808057 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2579. Min Act: -0.0002

Data Index: 1071326 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2660. Min Act: -0.0002

Data Index: 628982 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2660. Min Act: -0.0002

Data Index: 193672 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2579. Min Act: -0.0002

Data Index: 610729 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2578. Min Act: -0.0002

Data Index: 1154674 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2671. Min Act: -0.0002

Data Index: 938248 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2587. Min Act: -0.0002

Data Index: 724994 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2548. Min Act: -0.0002

Data Index: 799536 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2561. Min Act: -0.0002

Data Index: 803531 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2458. Min Act: -0.0002

Data Index: 977158 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2558. Min Act: -0.0002

Data Index: 1121820 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2523. Min Act: -0.0002

Data Index: 653685 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.2766. Min Range: -0.2766

Max Act: 0.2518. Min Act: -0.0002

Data Index: 672667 (C4 (Web Text))

Max Activating Token Index: 557