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

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

Neuron 5257 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: 2.5497. Min Range: -2.5497

Max Act: 2.5497. Min Act: -0.0000

Data Index: 573362 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.4462. Min Act: -0.0000

Data Index: 1179168 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.4446. Min Act: -0.0000

Data Index: 242704 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.3980. Min Act: -0.0000

Data Index: 287545 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.1692. Min Act: -0.0000

Data Index: 429810 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.2633. Min Act: -0.0000

Data Index: 1131778 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.2167. Min Act: -0.0000

Data Index: 1020756 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.1731. Min Act: -0.0000

Data Index: 860511 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.2813. Min Act: -0.0000

Data Index: 873063 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 2.5497. Min Range: -2.5497

Max Act: 1.9793. Min Act: -0.0000

Data Index: 629465 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 2.5497. Min Range: -2.5497

Max Act: 1.9909. Min Act: -0.0000

Data Index: 783491 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 2.5497. Min Range: -2.5497

Max Act: 1.9605. Min Act: -0.0000

Data Index: 905892 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.0824. Min Act: -0.0000

Data Index: 950454 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.1745. Min Act: -0.0000

Data Index: 1059232 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.0037. Min Act: -0.0000

Data Index: 990384 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.1019. Min Act: -0.0000

Data Index: 369929 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 2.5497. Min Range: -2.5497

Max Act: 2.1077. Min Act: -0.0000

Data Index: 1112342 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 2.5497. Min Range: -2.5497

Max Act: 1.9389. Min Act: -0.0000

Data Index: 286041 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 2.5497. Min Range: -2.5497

Max Act: 1.8472. Min Act: -0.0000

Data Index: 645979 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 2.5497. Min Range: -2.5497

Max Act: 1.9231. Min Act: -0.0000

Data Index: 806807 (C4 (Web Text))

Max Activating Token Index: 30