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

Dataset: The Pile

Neuron 1947 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.9275. Min Act: 0.0000

Data Index: 491468 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.8119. Min Act: -0.0000

Data Index: 558869 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.7600. Min Act: -0.0000

Data Index: 702873 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.7297. Min Act: -0.0000

Data Index: 973898 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1988297 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6893. Min Act: -0.0000

Data Index: 930561 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6895. Min Act: -0.0000

Data Index: 581008 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6598. Min Act: 0.0001

Data Index: 1193874 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6649. Min Act: -0.0000

Data Index: 701354 (The Pile)

Max Activating Token Index: 278

Text #9

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1591977 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.5924. Min Act: -0.0000

Data Index: 299027 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.5827. Min Act: -0.0000

Data Index: 442757 (The Pile)

Max Activating Token Index: 943

Text #12

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6003. Min Act: 0.0000

Data Index: 403407 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1129775 (The Pile)

Max Activating Token Index: 301

Text #14

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6304. Min Act: -0.0000

Data Index: 1455941 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.5590. Min Act: 0.0000

Data Index: 1276548 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1077024 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.5738. Min Act: -0.0000

Data Index: 573938 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.5909. Min Act: -0.0000

Data Index: 732234 (The Pile)

Max Activating Token Index: 779

Text #19

Max Range: 0.9275. Min Range: -0.9275

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1817647 (The Pile)

Max Activating Token Index: 444