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

Dataset: The Pile

Neuron 2183 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6859. Min Act: -0.0000

Data Index: 221703 (The Pile)

Max Activating Token Index: 919

Text #1

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1570418 (The Pile)

Max Activating Token Index: 600

Text #2

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6958. Min Act: 0.0001

Data Index: 981964 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.7222. Min Act: -0.0000

Data Index: 224617 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1830166 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1665398 (The Pile)

Max Activating Token Index: 902

Text #6

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1389178 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6537. Min Act: -0.0000

Data Index: 174799 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6262. Min Act: 0.0000

Data Index: 232694 (The Pile)

Max Activating Token Index: 160

Text #9

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1053005 (The Pile)

Max Activating Token Index: 625

Text #10

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6031. Min Act: -0.0000

Data Index: 394140 (The Pile)

Max Activating Token Index: 62

Text #11

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5937. Min Act: -0.0000

Data Index: 974589 (The Pile)

Max Activating Token Index: 208

Text #12

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1138931 (The Pile)

Max Activating Token Index: 174

Text #13

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5802. Min Act: -0.0000

Data Index: 191905 (The Pile)

Max Activating Token Index: 548

Text #14

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1951809 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5711. Min Act: -0.0000

Data Index: 960252 (The Pile)

Max Activating Token Index: 839

Text #16

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5685. Min Act: -0.0000

Data Index: 396655 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5435. Min Act: -0.0000

Data Index: 561222 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5324. Min Act: -0.0000

Data Index: 153531 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 0.7222. Min Range: -0.7222

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1349618 (The Pile)

Max Activating Token Index: 140