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

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

Neuron 5334 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3513. Min Range: -5.3513

Max Act: 5.3513. Min Act: -0.0000

Data Index: 633197 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 5.3513. Min Range: -5.3513

Max Act: 5.1837. Min Act: -0.0000

Data Index: 407216 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.9751. Min Act: -0.0000

Data Index: 691163 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.8139. Min Act: -0.0000

Data Index: 1082109 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.9048. Min Act: -0.0000

Data Index: 106390 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.7824. Min Act: -0.0000

Data Index: 1257083 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.7033. Min Act: -0.0000

Data Index: 1136908 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 5.3513. Min Range: -5.3513

Max Act: 5.0928. Min Act: -0.0000

Data Index: 650598 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.8944. Min Act: -0.0000

Data Index: 1335667 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.9746. Min Act: -0.0000

Data Index: 51468 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.6091. Min Act: -0.0000

Data Index: 900238 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.7305. Min Act: -0.0000

Data Index: 111348 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.3767. Min Act: -0.0000

Data Index: 319303 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.5416. Min Act: -0.0000

Data Index: 131448 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.8957. Min Act: -0.0000

Data Index: 489976 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.7135. Min Act: -0.0000

Data Index: 622375 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.9042. Min Act: -0.0000

Data Index: 332095 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.7227. Min Act: -0.0000

Data Index: 87679 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.9125. Min Act: -0.0000

Data Index: 672060 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 5.3513. Min Range: -5.3513

Max Act: 4.8212. Min Act: -0.0000

Data Index: 174883 (C4 (Web Text))

Max Activating Token Index: 42