Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4557 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1898061 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5998. Min Act: -0.0000

Data Index: 217129 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6760. Min Act: -0.0000

Data Index: 1286235 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1420882 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6572. Min Act: -0.0000

Data Index: 113644 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1808024 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6081. Min Act: -0.0000

Data Index: 405515 (The Pile)

Max Activating Token Index: 985

Text #7

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1043226 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1344907 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1079623 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6514. Min Act: -0.0000

Data Index: 510566 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1776832 (The Pile)

Max Activating Token Index: 1007

Text #12

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1442062 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6206. Min Act: -0.0000

Data Index: 37498 (The Pile)

Max Activating Token Index: 875

Text #14

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1280796 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5440. Min Act: -0.0000

Data Index: 721378 (The Pile)

Max Activating Token Index: 651

Text #16

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5790. Min Act: -0.0000

Data Index: 625819 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5137. Min Act: -0.0000

Data Index: 285239 (The Pile)

Max Activating Token Index: 713

Text #18

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5504. Min Act: -0.0000

Data Index: 672188 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 0.6879. Min Range: -0.6879

Max Act: 0.5435. Min Act: -0.0000

Data Index: 413196 (The Pile)

Max Activating Token Index: 289