Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1947 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0906. Min Act: -0.0001

Data Index: 977029 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0001

Data Index: 948535 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0914. Min Act: -0.0001

Data Index: 949714 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1076605 (C4 (Web Text))

Max Activating Token Index: 998

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0900. Min Act: -0.0001

Data Index: 1120051 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0857. Min Act: -0.0001

Data Index: 1234111 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0881. Min Act: -0.0001

Data Index: 338931 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0834. Min Act: -0.0001

Data Index: 484077 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0835. Min Act: -0.0001

Data Index: 476970 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0799. Min Act: -0.0001

Data Index: 84829 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0789. Min Act: -0.0001

Data Index: 473760 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1189578 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0838. Min Act: -0.0001

Data Index: 316300 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0818. Min Act: -0.0001

Data Index: 37990 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0778. Min Act: -0.0001

Data Index: 924318 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0769. Min Act: -0.0001

Data Index: 849178 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0729. Min Act: -0.0001

Data Index: 659610 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0736. Min Act: -0.0001

Data Index: 961037 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0766. Min Act: -0.0001

Data Index: 166072 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0791. Min Act: -0.0001

Data Index: 237284 (C4 (Web Text))

Max Activating Token Index: 35