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

Dataset: The Pile

Neuron 2969 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: 1.0093. Min Range: -1.0093

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1645465 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.9824. Min Act: -0.0000

Data Index: 1817285 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.9034. Min Act: -0.0000

Data Index: 439176 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1670891 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8840. Min Act: -0.0000

Data Index: 560560 (The Pile)

Max Activating Token Index: 281

Text #5

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1228942 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1277701 (The Pile)

Max Activating Token Index: 219

Text #7

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1142754 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8234. Min Act: -0.0000

Data Index: 856898 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8223. Min Act: -0.0000

Data Index: 750589 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1890835 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1261794 (The Pile)

Max Activating Token Index: 575

Text #12

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8282. Min Act: -0.0001

Data Index: 610737 (The Pile)

Max Activating Token Index: 37

Text #13

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8237. Min Act: -0.0000

Data Index: 460305 (The Pile)

Max Activating Token Index: 11

Text #14

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7417. Min Act: -0.0000

Data Index: 611079 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7643. Min Act: -0.0000

Data Index: 1714885 (The Pile)

Max Activating Token Index: 375

Text #16

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1509635 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1109092 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8094. Min Act: -0.0000

Data Index: 295901 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 1.0093. Min Range: -1.0093

Max Act: 0.8519. Min Act: -0.0000

Data Index: 793973 (The Pile)

Max Activating Token Index: 84