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

Dataset: The Pile

Neuron 226 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: 0.2239. Min Range: -0.2239

Max Act: 0.2239. Min Act: -0.0000

Data Index: 955528 (The Pile)

Max Activating Token Index: 452

Text #1

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.2187. Min Act: -0.0000

Data Index: 574145 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.2018. Min Act: -0.0000

Data Index: 403109 (The Pile)

Max Activating Token Index: 365

Text #3

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1400751 (The Pile)

Max Activating Token Index: 989

Text #4

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1707. Min Act: -0.0000

Data Index: 1224943 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1689. Min Act: -0.0000

Data Index: 696153 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1043665 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1944. Min Act: -0.0000

Data Index: 1416982 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1507. Min Act: -0.0000

Data Index: 443828 (The Pile)

Max Activating Token Index: 727

Text #9

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1708. Min Act: -0.0000

Data Index: 913790 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1642. Min Act: -0.0000

Data Index: 839857 (The Pile)

Max Activating Token Index: 715

Text #11

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1765. Min Act: -0.0000

Data Index: 341057 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1943583 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1113686 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1464. Min Act: -0.0000

Data Index: 136924 (The Pile)

Max Activating Token Index: 931

Text #15

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1496. Min Act: -0.0000

Data Index: 483659 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1808331 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1416. Min Act: -0.0000

Data Index: 1431992 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1498. Min Act: -0.0000

Data Index: 877624 (The Pile)

Max Activating Token Index: 529

Text #19

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1814156 (The Pile)

Max Activating Token Index: 140