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

Dataset: The Pile

Neuron 3286 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.1078. Min Act: -0.0000

Data Index: 652729 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.0716. Min Act: -0.0000

Data Index: 719049 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1132867 (The Pile)

Max Activating Token Index: 843

Text #3

Max Range: 1.1078. Min Range: -1.1078

Max Act: 1.0362. Min Act: -0.0000

Data Index: 336583 (The Pile)

Max Activating Token Index: 978

Text #4

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1035321 (The Pile)

Max Activating Token Index: 888

Text #5

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1956135 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.9763. Min Act: -0.0000

Data Index: 1695347 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1038068 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8552. Min Act: 0.0000

Data Index: 1664939 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8564. Min Act: -0.0000

Data Index: 987538 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8567. Min Act: -0.0000

Data Index: 221578 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8878. Min Act: -0.0000

Data Index: 195899 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8281. Min Act: -0.0000

Data Index: 110184 (The Pile)

Max Activating Token Index: 547

Text #13

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8036. Min Act: -0.0000

Data Index: 620982 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8009. Min Act: -0.0000

Data Index: 481232 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8237. Min Act: -0.0000

Data Index: 868364 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1590735 (The Pile)

Max Activating Token Index: 645

Text #17

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.7695. Min Act: -0.0000

Data Index: 286036 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1091585 (The Pile)

Max Activating Token Index: 723

Text #19

Max Range: 1.1078. Min Range: -1.1078

Max Act: 0.8477. Min Act: -0.0000

Data Index: 476617 (The Pile)

Max Activating Token Index: 48