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

Dataset: The Pile

Neuron 1233 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1974842 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.9384. Min Act: -0.0000

Data Index: 462674 (The Pile)

Max Activating Token Index: 892

Text #2

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1133000 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.7076. Min Act: -0.0000

Data Index: 1803429 (The Pile)

Max Activating Token Index: 957

Text #4

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1107112 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1358272 (The Pile)

Max Activating Token Index: 364

Text #6

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1460945 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6059. Min Act: -0.0000

Data Index: 615247 (The Pile)

Max Activating Token Index: 946

Text #8

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1605434 (The Pile)

Max Activating Token Index: 945

Text #9

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1676169 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1201249 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.5952. Min Act: -0.0000

Data Index: 574724 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.5762. Min Act: -0.0000

Data Index: 1569496 (The Pile)

Max Activating Token Index: 1003

Text #13

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1804553 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1811449 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1732251 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6609. Min Act: -0.0000

Data Index: 314195 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1001607 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.5889. Min Act: -0.0000

Data Index: 174772 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 0.9555. Min Range: -0.9555

Max Act: 0.6234. Min Act: -0.0000

Data Index: 727804 (The Pile)

Max Activating Token Index: 388