Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 967 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6804. Min Act: -0.0000

Data Index: 322281 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1460472 (The Pile)

Max Activating Token Index: 871

Text #2

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6611. Min Act: -0.0000

Data Index: 811327 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1457668 (The Pile)

Max Activating Token Index: 793

Text #4

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6283. Min Act: -0.0000

Data Index: 152489 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6364. Min Act: -0.0000

Data Index: 485219 (The Pile)

Max Activating Token Index: 668

Text #6

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6292. Min Act: -0.0000

Data Index: 540381 (The Pile)

Max Activating Token Index: 241

Text #7

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1529246 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6104. Min Act: -0.0000

Data Index: 810124 (The Pile)

Max Activating Token Index: 724

Text #9

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1174308 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1210124 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1826278 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5667. Min Act: -0.0000

Data Index: 586252 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1735827 (The Pile)

Max Activating Token Index: 615

Text #14

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1928653 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5532. Min Act: -0.0000

Data Index: 769522 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5733. Min Act: -0.0000

Data Index: 710902 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5762. Min Act: -0.0000

Data Index: 302550 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1028860 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5932. Min Act: -0.0000

Data Index: 923963 (The Pile)

Max Activating Token Index: 673