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

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

Neuron 1422 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: 0.5044. Min Range: -0.5044

Max Act: 0.5044. Min Act: -0.0002

Data Index: 1124818 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3828. Min Act: -0.0002

Data Index: 791114 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.4055. Min Act: -0.0002

Data Index: 1148137 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3806. Min Act: -0.0002

Data Index: 380670 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3891. Min Act: -0.0002

Data Index: 413719 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3814. Min Act: -0.0002

Data Index: 415085 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3475. Min Act: -0.0002

Data Index: 868022 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3721. Min Act: -0.0002

Data Index: 530379 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3464. Min Act: -0.0002

Data Index: 908188 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3629. Min Act: -0.0002

Data Index: 181495 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3499. Min Act: -0.0002

Data Index: 1083893 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3836. Min Act: -0.0002

Data Index: 889778 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3545. Min Act: -0.0002

Data Index: 116200 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3338. Min Act: -0.0002

Data Index: 379957 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3540. Min Act: -0.0002

Data Index: 1220752 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3453. Min Act: -0.0002

Data Index: 1069894 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3501. Min Act: -0.0002

Data Index: 913870 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3456. Min Act: -0.0002

Data Index: 297908 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3467. Min Act: -0.0002

Data Index: 810709 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.5044. Min Range: -0.5044

Max Act: 0.3228. Min Act: -0.0002

Data Index: 197300 (C4 (Web Text))

Max Activating Token Index: 144