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

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

Neuron 2755 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: 0.7050. Min Range: -0.7050

Max Act: 0.7050. Min Act: -0.0000

Data Index: 110404 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.6289. Min Act: -0.0000

Data Index: 12514 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5811. Min Act: -0.0000

Data Index: 659207 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5471. Min Act: -0.0000

Data Index: 102230 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1039838 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5289. Min Act: -0.0000

Data Index: 599165 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5109. Min Act: -0.0000

Data Index: 962330 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.4937. Min Act: -0.0000

Data Index: 1036534 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1081041 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5255. Min Act: -0.0000

Data Index: 908254 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.4974. Min Act: -0.0000

Data Index: 421014 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.4918. Min Act: -0.0000

Data Index: 274934 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5206. Min Act: -0.0000

Data Index: 563281 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5061. Min Act: -0.0000

Data Index: 345079 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1213568 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1035101 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1020331 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.4621. Min Act: -0.0000

Data Index: 871466 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.5057. Min Act: -0.0000

Data Index: 854626 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.7050. Min Range: -0.7050

Max Act: 0.4575. Min Act: -0.0000

Data Index: 968603 (C4 (Web Text))

Max Activating Token Index: 250