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

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

Neuron 5392 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.3771. Min Act: -0.0001

Data Index: 263743 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2548. Min Act: -0.0001

Data Index: 14459 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2255. Min Act: -0.0001

Data Index: 31974 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2092. Min Act: -0.0000

Data Index: 328022 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1111096 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2038. Min Act: -0.0001

Data Index: 546968 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1190744 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1017912 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2141. Min Act: -0.0001

Data Index: 817213 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2383. Min Act: -0.0001

Data Index: 1329681 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2090. Min Act: -0.0001

Data Index: 784255 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2175. Min Act: -0.0001

Data Index: 719201 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2108. Min Act: -0.0000

Data Index: 831833 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.1952. Min Act: -0.0001

Data Index: 706137 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2101. Min Act: -0.0001

Data Index: 216723 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2011. Min Act: -0.0000

Data Index: 756056 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.2012. Min Act: -0.0001

Data Index: 662049 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1140910 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.1931. Min Act: -0.0001

Data Index: 544161 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.3771. Min Range: -0.3771

Max Act: 0.1878. Min Act: -0.0001

Data Index: 1177503 (C4 (Web Text))

Max Activating Token Index: 758