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

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

Neuron 1706 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2870. Min Act: -0.0003

Data Index: 411727 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2668. Min Act: -0.0002

Data Index: 584584 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2387. Min Act: -0.0002

Data Index: 791445 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2345. Min Act: -0.0003

Data Index: 85189 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2303. Min Act: -0.0002

Data Index: 1119260 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2065. Min Act: -0.0002

Data Index: 1330571 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.2040. Min Act: -0.0003

Data Index: 480234 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1983. Min Act: -0.0003

Data Index: 984072 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1948. Min Act: -0.0003

Data Index: 932086 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1898. Min Act: -0.0003

Data Index: 31530 (C4 (Web Text))

Max Activating Token Index: 458

Text #10

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1899. Min Act: -0.0003

Data Index: 271066 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1876. Min Act: -0.0003

Data Index: 1337752 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1807. Min Act: -0.0003

Data Index: 1018216 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1850. Min Act: -0.0003

Data Index: 153734 (C4 (Web Text))

Max Activating Token Index: 158

Text #14

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1833. Min Act: -0.0003

Data Index: 815385 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1830. Min Act: -0.0003

Data Index: 1013070 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1797. Min Act: -0.0002

Data Index: 394152 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1781. Min Act: -0.0003

Data Index: 921903 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1703. Min Act: -0.0003

Data Index: 1322345 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.2870. Min Range: -0.2870

Max Act: 0.1757. Min Act: -0.0002

Data Index: 872273 (C4 (Web Text))

Max Activating Token Index: 306