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

Dataset: The Pile

Neuron 355 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: 0.7235. Min Range: -0.7235

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1526366 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6550. Min Act: 0.0000

Data Index: 935334 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5939. Min Act: 0.0002

Data Index: 1141588 (The Pile)

Max Activating Token Index: 921

Text #3

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1828510 (The Pile)

Max Activating Token Index: 985

Text #4

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1290154 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.6469. Min Act: -0.0000

Data Index: 230755 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5759. Min Act: -0.0000

Data Index: 1340686 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5961. Min Act: 0.0001

Data Index: 1121688 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1424483 (The Pile)

Max Activating Token Index: 291

Text #9

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1438864 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1103915 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5136. Min Act: -0.0000

Data Index: 68434 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.5287. Min Act: 0.0000

Data Index: 575979 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1134420 (The Pile)

Max Activating Token Index: 202

Text #14

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1282342 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1397497 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.4708. Min Act: 0.0000

Data Index: 1218850 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.4707. Min Act: 0.0002

Data Index: 1874360 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.4418. Min Act: -0.0000

Data Index: 518959 (The Pile)

Max Activating Token Index: 364

Text #19

Max Range: 0.7235. Min Range: -0.7235

Max Act: 0.4418. Min Act: 0.0003

Data Index: 965438 (The Pile)

Max Activating Token Index: 518