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

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

Neuron 5182 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: 0.3523. Min Range: -0.3523

Max Act: 0.3523. Min Act: -0.0000

Data Index: 87463 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1156512 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1012366 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3045. Min Act: -0.0000

Data Index: 740635 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1102049 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2400. Min Act: -0.0000

Data Index: 441659 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2147. Min Act: -0.0000

Data Index: 304868 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.1913. Min Act: -0.0000

Data Index: 271908 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2109. Min Act: -0.0000

Data Index: 970794 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1097647 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1330944 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2017. Min Act: -0.0000

Data Index: 205995 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.1956. Min Act: -0.0000

Data Index: 89881 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.1969. Min Act: -0.0000

Data Index: 498667 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1192430 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1243597 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.1854. Min Act: -0.0000

Data Index: 735523 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1248012 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1002791 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.1887. Min Act: 0.0000

Data Index: 300973 (C4 (Web Text))

Max Activating Token Index: 535