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

Dataset: The Pile

Neuron 2279 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.9724. Min Act: -0.0000

Data Index: 275682 (The Pile)

Max Activating Token Index: 398

Text #1

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1669044 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1713146 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5927. Min Act: -0.0000

Data Index: 949161 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1598810 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.6529. Min Act: -0.0000

Data Index: 598534 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1189851 (The Pile)

Max Activating Token Index: 240

Text #7

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5831. Min Act: -0.0000

Data Index: 1404173 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5634. Min Act: -0.0000

Data Index: 9279 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1972006 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1680768 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5758. Min Act: -0.0000

Data Index: 551423 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5895. Min Act: -0.0000

Data Index: 259266 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1851493 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5509. Min Act: -0.0000

Data Index: 256309 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1222473 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1310625 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5756. Min Act: -0.0000

Data Index: 328197 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1287233 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 0.9724. Min Range: -0.9724

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1462356 (The Pile)

Max Activating Token Index: 169