Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 191 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.5171. Min Act: -0.0000

Data Index: 201861 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.3590. Min Act: -0.0000

Data Index: 2975 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.3093. Min Act: -0.0000

Data Index: 1034817 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.4055. Min Act: -0.0000

Data Index: 517402 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.2931. Min Act: -0.0000

Data Index: 184616 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.1727. Min Act: -0.0000

Data Index: 1282007 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.2221. Min Act: -0.0000

Data Index: 1148889 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1119556 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.0986. Min Act: -0.0000

Data Index: 832947 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.0875. Min Act: -0.0000

Data Index: 1126413 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1023162 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.0777. Min Act: -0.0000

Data Index: 435859 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.0090. Min Act: -0.0000

Data Index: 509286 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1144575 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.0530. Min Act: -0.0000

Data Index: 453950 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.0071. Min Act: -0.0000

Data Index: 710702 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.1079. Min Act: -0.0000

Data Index: 497414 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.5171. Min Range: -1.5171

Max Act: 0.9688. Min Act: -0.0000

Data Index: 562912 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.5171. Min Range: -1.5171

Max Act: 1.0418. Min Act: -0.0000

Data Index: 427916 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 1.5171. Min Range: -1.5171

Max Act: 0.9391. Min Act: -0.0000

Data Index: 23730 (C4 (Web Text))

Max Activating Token Index: 755