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

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

Neuron 111 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8830. Min Act: -0.0000

Data Index: 832875 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8778. Min Act: -0.0000

Data Index: 110714 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.8808. Min Act: -0.0000

Data Index: 463976 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.7914. Min Act: -0.0000

Data Index: 328652 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.6822. Min Act: -0.0000

Data Index: 304818 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.6956. Min Act: -0.0000

Data Index: 672835 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.6952. Min Act: 0.0000

Data Index: 1333031 (C4 (Web Text))

Max Activating Token Index: 638

Text #7

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.5910. Min Act: -0.0000

Data Index: 823410 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.6392. Min Act: -0.0000

Data Index: 857731 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1221074 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1273639 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1057139 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.6115. Min Act: -0.0000

Data Index: 146496 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1165527 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1152126 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.5951. Min Act: -0.0000

Data Index: 655624 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1246881 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.5758. Min Act: -0.0000

Data Index: 604947 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.5479. Min Act: -0.0000

Data Index: 452907 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.8830. Min Range: -0.8830

Max Act: 0.5857. Min Act: -0.0000

Data Index: 91119 (C4 (Web Text))

Max Activating Token Index: 503