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

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

Neuron 4569 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: 0.6673. Min Range: -0.6673

Max Act: 0.6673. Min Act: -0.0000

Data Index: 490878 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.6435. Min Act: -0.0000

Data Index: 674165 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5563. Min Act: 0.0000

Data Index: 685801 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5706. Min Act: -0.0000

Data Index: 209004 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5455. Min Act: -0.0000

Data Index: 442616 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5133. Min Act: -0.0000

Data Index: 423778 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5234. Min Act: -0.0000

Data Index: 717725 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.5062. Min Act: -0.0000

Data Index: 354575 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1029942 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1138249 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1175847 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4705. Min Act: -0.0000

Data Index: 274985 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4745. Min Act: -0.0000

Data Index: 50252 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1084816 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1115828 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1300689 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4291. Min Act: -0.0000

Data Index: 162199 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4368. Min Act: -0.0000

Data Index: 43086 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4375. Min Act: -0.0000

Data Index: 902348 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.6673. Min Range: -0.6673

Max Act: 0.4203. Min Act: -0.0000

Data Index: 467793 (C4 (Web Text))

Max Activating Token Index: 614