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

Dataset: The Pile

Neuron 2621 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7604. Min Act: -0.0000

Data Index: 572547 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.8567. Min Act: -0.0000

Data Index: 213862 (The Pile)

Max Activating Token Index: 824

Text #2

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6817. Min Act: -0.0000

Data Index: 499487 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6451. Min Act: -0.0000

Data Index: 1673817 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6867. Min Act: -0.0000

Data Index: 733414 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6306. Min Act: -0.0000

Data Index: 951203 (The Pile)

Max Activating Token Index: 1001

Text #6

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1916762 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6898. Min Act: -0.0000

Data Index: 1875427 (The Pile)

Max Activating Token Index: 664

Text #8

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6081. Min Act: -0.0000

Data Index: 130702 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6800. Min Act: -0.0000

Data Index: 706097 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1006300 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1233351 (The Pile)

Max Activating Token Index: 767

Text #12

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1824088 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6132. Min Act: -0.0000

Data Index: 1381200 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1389774 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1166032 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1870199 (The Pile)

Max Activating Token Index: 407

Text #17

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1579301 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6362. Min Act: -0.0000

Data Index: 316864 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.5683. Min Act: 0.0000

Data Index: 1003228 (The Pile)

Max Activating Token Index: 92