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

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

Neuron 4477 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: 1.7103. Min Range: -1.7103

Max Act: 1.7103. Min Act: -0.0000

Data Index: 179153 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.4948. Min Act: -0.0000

Data Index: 954515 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.4024. Min Act: -0.0000

Data Index: 427548 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.3751. Min Act: -0.0000

Data Index: 5038 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.4203. Min Act: -0.0000

Data Index: 1200992 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.2793. Min Act: -0.0000

Data Index: 1047029 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.2164. Min Act: -0.0000

Data Index: 506197 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.2959. Min Act: -0.0000

Data Index: 400905 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.2924. Min Act: -0.0000

Data Index: 1264766 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.1997. Min Act: -0.0000

Data Index: 88679 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.2240. Min Act: -0.0000

Data Index: 542610 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.0822. Min Act: -0.0000

Data Index: 723187 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1250720 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.1117. Min Act: -0.0000

Data Index: 261979 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.0510. Min Act: -0.0000

Data Index: 722083 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.0735. Min Act: -0.0000

Data Index: 468618 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.7103. Min Range: -1.7103

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1235736 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.0543. Min Act: -0.0000

Data Index: 194059 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 1.7103. Min Range: -1.7103

Max Act: 0.9942. Min Act: -0.0000

Data Index: 498418 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 1.7103. Min Range: -1.7103

Max Act: 1.0090. Min Act: -0.0000

Data Index: 869391 (C4 (Web Text))

Max Activating Token Index: 610