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

Dataset: The Pile

Neuron 319 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: 0.3161. Min Range: -0.3161

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1710901 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2432. Min Act: -0.0000

Data Index: 893495 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1858856 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2858. Min Act: -0.0000

Data Index: 543563 (The Pile)

Max Activating Token Index: 99

Text #4

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2527. Min Act: -0.0000

Data Index: 1419908 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2405. Min Act: -0.0000

Data Index: 100166 (The Pile)

Max Activating Token Index: 767

Text #6

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2372. Min Act: -0.0000

Data Index: 574795 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1624398 (The Pile)

Max Activating Token Index: 149

Text #8

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2326. Min Act: -0.0000

Data Index: 289261 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1747920 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2017. Min Act: -0.0000

Data Index: 831117 (The Pile)

Max Activating Token Index: 138

Text #11

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2049. Min Act: -0.0000

Data Index: 281231 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1716666 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1320329 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1272935 (The Pile)

Max Activating Token Index: 626

Text #15

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2111. Min Act: -0.0000

Data Index: 926882 (The Pile)

Max Activating Token Index: 24

Text #16

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2052. Min Act: -0.0000

Data Index: 1224425 (The Pile)

Max Activating Token Index: 602

Text #17

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2159. Min Act: -0.0000

Data Index: 992773 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.2245. Min Act: -0.0000

Data Index: 539112 (The Pile)

Max Activating Token Index: 279

Text #19

Max Range: 0.3161. Min Range: -0.3161

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1573305 (The Pile)

Max Activating Token Index: 324