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

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

Neuron 2706 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: 2.2044. Min Range: -2.2044

Max Act: 2.1141. Min Act: -0.0000

Data Index: 80028 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 2.2044. Min Range: -2.2044

Max Act: 2.1229. Min Act: -0.0000

Data Index: 395074 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 2.2044. Min Range: -2.2044

Max Act: 2.0033. Min Act: -0.0000

Data Index: 1179309 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 2.2044. Min Range: -2.2044

Max Act: 2.2044. Min Act: -0.0000

Data Index: 143440 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.9930. Min Act: -0.0000

Data Index: 969770 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 2.2044. Min Range: -2.2044

Max Act: 2.0076. Min Act: -0.0000

Data Index: 1245827 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.9336. Min Act: -0.0000

Data Index: 820956 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.6842. Min Act: -0.0000

Data Index: 692922 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.8016. Min Act: -0.0000

Data Index: 833855 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.7523. Min Act: -0.0000

Data Index: 735367 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.7325. Min Act: -0.0000

Data Index: 53586 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.8379. Min Act: -0.0000

Data Index: 27742 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.8166. Min Act: -0.0000

Data Index: 241561 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.6370. Min Act: -0.0000

Data Index: 237021 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.6799. Min Act: -0.0000

Data Index: 695245 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.7478. Min Act: -0.0000

Data Index: 413712 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.7317. Min Act: -0.0000

Data Index: 800024 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.4623. Min Act: -0.0000

Data Index: 798945 (C4 (Web Text))

Max Activating Token Index: 153

Text #18

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.5615. Min Act: -0.0000

Data Index: 843346 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 2.2044. Min Range: -2.2044

Max Act: 1.5508. Min Act: -0.0000

Data Index: 59106 (C4 (Web Text))

Max Activating Token Index: 94