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

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

Neuron 2924 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6955. Min Act: -0.0000

Data Index: 916206 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4993. Min Act: -0.0000

Data Index: 118906 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1224577 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4972. Min Act: -0.0000

Data Index: 917965 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.3988. Min Act: -0.0000

Data Index: 295495 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.3902. Min Act: -0.0000

Data Index: 231861 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1169807 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.3153. Min Act: -0.0000

Data Index: 312683 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1338272 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1209702 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.2882. Min Act: -0.0000

Data Index: 903086 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.3033. Min Act: -0.0000

Data Index: 799272 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.2741. Min Act: -0.0000

Data Index: 116873 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1330888 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.2633. Min Act: -0.0000

Data Index: 28402 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1322759 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.2023. Min Act: -0.0000

Data Index: 924952 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1004797 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1312426 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.2202. Min Act: -0.0000

Data Index: 866932 (C4 (Web Text))

Max Activating Token Index: 690