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

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

Neuron 496 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.0333. Min Act: -0.0000

Data Index: 351470 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.3581. Min Act: -0.0000

Data Index: 736756 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.4638. Min Act: -0.0000

Data Index: 958627 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.4415. Min Act: -0.0000

Data Index: 642165 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.3098. Min Act: -0.0000

Data Index: 638494 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.2929. Min Act: -0.0000

Data Index: 738705 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.3111. Min Act: -0.0000

Data Index: 1545440 (Python Code)

Max Activating Token Index: 818

Text #7

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.2979. Min Act: -0.0000

Data Index: 119317 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.2739. Min Act: -0.0000

Data Index: 650892 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.2402. Min Act: -0.0000

Data Index: 69207 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.1213. Min Act: -0.0000

Data Index: 968516 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.4634. Min Act: -0.0000

Data Index: 1171074 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.2038. Min Act: -0.0000

Data Index: 892067 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.1778. Min Act: -0.0000

Data Index: 1270649 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.1474. Min Act: -0.0000

Data Index: 1074247 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.0550. Min Act: -0.0000

Data Index: 738097 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.0248. Min Act: -0.0000

Data Index: 1143114 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 2.4638. Min Range: -2.4638

Max Act: 2.1313. Min Act: -0.0000

Data Index: 326287 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 2.4638. Min Range: -2.4638

Max Act: 1.9022. Min Act: -0.0000

Data Index: 1036752 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 2.4638. Min Range: -2.4638

Max Act: 1.9037. Min Act: -0.0000

Data Index: 1063041 (C4 (Web Text))

Max Activating Token Index: 244