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

Dataset: The Pile

Neuron 61 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1787280 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1854626 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7811. Min Act: -0.0000

Data Index: 514409 (The Pile)

Max Activating Token Index: 358

Text #3

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7298. Min Act: -0.0000

Data Index: 259150 (The Pile)

Max Activating Token Index: 494

Text #4

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.8748. Min Act: -0.0000

Data Index: 794405 (The Pile)

Max Activating Token Index: 951

Text #5

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.8448. Min Act: -0.0000

Data Index: 195896 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1379012 (The Pile)

Max Activating Token Index: 110

Text #7

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7372. Min Act: -0.0000

Data Index: 395945 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1200088 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7246. Min Act: -0.0000

Data Index: 479957 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7397. Min Act: -0.0000

Data Index: 513970 (The Pile)

Max Activating Token Index: 193

Text #11

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7026. Min Act: -0.0000

Data Index: 894488 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1732996 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.6892. Min Act: -0.0000

Data Index: 1015845 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1161906 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7363. Min Act: -0.0001

Data Index: 1390046 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1324060 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.6754. Min Act: -0.0000

Data Index: 423390 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.6899. Min Act: -0.0001

Data Index: 121589 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1460384 (The Pile)

Max Activating Token Index: 174