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

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

Neuron 2912 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1572. Min Range: -2.1572

Max Act: 2.1021. Min Act: -0.0000

Data Index: 1239209 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 2.1572. Min Range: -2.1572

Max Act: 2.1052. Min Act: -0.0000

Data Index: 266935 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 2.1572. Min Range: -2.1572

Max Act: 2.1572. Min Act: -0.0000

Data Index: 140275 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.8545. Min Act: -0.0000

Data Index: 645822 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.9406. Min Act: -0.0000

Data Index: 1239726 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.8042. Min Act: -0.0000

Data Index: 872796 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.9015. Min Act: -0.0000

Data Index: 411540 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.9754. Min Act: -0.0000

Data Index: 115986 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.8412. Min Act: -0.0000

Data Index: 638875 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.8179. Min Act: -0.0000

Data Index: 432309 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.6712. Min Act: -0.0000

Data Index: 112191 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.8719. Min Act: -0.0000

Data Index: 247066 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.7268. Min Act: -0.0000

Data Index: 1278103 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.6111. Min Act: -0.0000

Data Index: 154835 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.8001. Min Act: -0.0000

Data Index: 880671 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.6171. Min Act: -0.0000

Data Index: 180014 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.7364. Min Act: -0.0000

Data Index: 1138872 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.5642. Min Act: -0.0000

Data Index: 996367 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.5368. Min Act: -0.0000

Data Index: 563010 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 2.1572. Min Range: -2.1572

Max Act: 1.4542. Min Act: -0.0000

Data Index: 354797 (C4 (Web Text))

Max Activating Token Index: 120