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

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

Neuron 3141 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2634. Min Act: -0.0000

Data Index: 891653 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2295. Min Act: -0.0001

Data Index: 1008941 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2325. Min Act: -0.0000

Data Index: 549169 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1004910 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2295. Min Act: -0.0001

Data Index: 728583 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2282. Min Act: -0.0001

Data Index: 906550 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2204. Min Act: -0.0001

Data Index: 782722 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2208. Min Act: -0.0000

Data Index: 832425 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2192. Min Act: -0.0000

Data Index: 730922 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2114. Min Act: -0.0001

Data Index: 951530 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2178. Min Act: -0.0000

Data Index: 95795 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2034. Min Act: -0.0001

Data Index: 1025080 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2110. Min Act: -0.0000

Data Index: 755999 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2186. Min Act: -0.0001

Data Index: 225283 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1342705 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1065121 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2008. Min Act: -0.0000

Data Index: 757589 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1997. Min Act: -0.0001

Data Index: 734044 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.2063. Min Act: -0.0001

Data Index: 720986 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.2634. Min Range: -0.2634

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1199669 (C4 (Web Text))

Max Activating Token Index: 1018