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

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

Neuron 3891 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: 0.1318. Min Range: -0.1318

Max Act: 0.1318. Min Act: -0.0000

Data Index: 144834 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1046. Min Act: -0.0000

Data Index: 183055 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1057. Min Act: -0.0000

Data Index: 928391 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1070. Min Act: -0.0000

Data Index: 310752 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1358263 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1031. Min Act: -0.0000

Data Index: 863066 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1032029 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0981. Min Act: -0.0000

Data Index: 392863 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1029. Min Act: -0.0000

Data Index: 284121 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0995. Min Act: -0.0000

Data Index: 471105 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1049. Min Act: -0.0000

Data Index: 967705 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0975. Min Act: -0.0000

Data Index: 418103 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1080. Min Act: -0.0000

Data Index: 17596 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1039. Min Act: -0.0000

Data Index: 841735 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0992. Min Act: -0.0000

Data Index: 135348 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0972. Min Act: -0.0000

Data Index: 529388 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.1008. Min Act: -0.0000

Data Index: 591617 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0967. Min Act: -0.0000

Data Index: 609046 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0964. Min Act: -0.0000

Data Index: 238509 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 0.1318. Min Range: -0.1318

Max Act: 0.0912. Min Act: -0.0000

Data Index: 40767 (C4 (Web Text))

Max Activating Token Index: 214