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

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

Neuron 4207 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.1027. Min Act: -0.0000

Data Index: 68785 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1037160 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.6851. Min Act: -0.0000

Data Index: 57638 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.7072. Min Act: -0.0000

Data Index: 335303 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.6471. Min Act: -0.0000

Data Index: 9682 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.6311. Min Act: -0.0000

Data Index: 498719 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.6168. Min Act: 0.0000

Data Index: 484551 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5768. Min Act: -0.0000

Data Index: 856629 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5986. Min Act: -0.0000

Data Index: 814740 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5753. Min Act: -0.0000

Data Index: 979076 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1269564 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5603. Min Act: -0.0000

Data Index: 91273 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5495. Min Act: -0.0000

Data Index: 823717 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1085456 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5539. Min Act: -0.0000

Data Index: 974606 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5253. Min Act: -0.0000

Data Index: 304047 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5342. Min Act: -0.0000

Data Index: 549221 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5404. Min Act: -0.0000

Data Index: 35476 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.5151. Min Act: -0.0000

Data Index: 955805 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.4937. Min Act: -0.0000

Data Index: 349108 (C4 (Web Text))

Max Activating Token Index: 1002