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

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

Neuron 5745 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.5695. Min Act: -0.0000

Data Index: 558058 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.3267. Min Act: -0.0000

Data Index: 151471 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.8896. Min Act: -0.0000

Data Index: 28424 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.1478. Min Act: -0.0000

Data Index: 912853 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 3.5695. Min Range: -3.5695

Max Act: 3.0577. Min Act: -0.0000

Data Index: 409577 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.9570. Min Act: -0.0000

Data Index: 199918 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.5212. Min Act: -0.0000

Data Index: 1087875 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.3180. Min Act: -0.0000

Data Index: 22885 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.4000. Min Act: -0.0000

Data Index: 690241 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.3730. Min Act: -0.0000

Data Index: 436730 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.3026. Min Act: -0.0000

Data Index: 1059861 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.1449. Min Act: -0.0000

Data Index: 632161 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.1925. Min Act: -0.0000

Data Index: 655580 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.2945. Min Act: -0.0000

Data Index: 1029749 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.1705. Min Act: -0.0000

Data Index: 1279100 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.0452. Min Act: -0.0000

Data Index: 452033 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.0363. Min Act: -0.0000

Data Index: 796162 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.0418. Min Act: -0.0000

Data Index: 1285300 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.1686. Min Act: -0.0000

Data Index: 42488 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 3.5695. Min Range: -3.5695

Max Act: 2.1545. Min Act: -0.0000

Data Index: 860867 (C4 (Web Text))

Max Activating Token Index: 915