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

Dataset: The Pile

Neuron 2611 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: 0.8792. Min Range: -0.8792

Max Act: 0.8792. Min Act: -0.0000

Data Index: 306294 (The Pile)

Max Activating Token Index: 366

Text #1

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8505. Min Act: -0.0000

Data Index: 602753 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1436222 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1346700 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1578350 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6940. Min Act: -0.0000

Data Index: 424943 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1051205 (The Pile)

Max Activating Token Index: 265

Text #7

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1043604 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6101. Min Act: -0.0000

Data Index: 1909314 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1587557 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6513. Min Act: -0.0000

Data Index: 11876 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6805. Min Act: -0.0000

Data Index: 78403 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1982013 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5645. Min Act: -0.0000

Data Index: 731520 (The Pile)

Max Activating Token Index: 208

Text #14

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6096. Min Act: -0.0000

Data Index: 514654 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5446. Min Act: -0.0000

Data Index: 210281 (The Pile)

Max Activating Token Index: 918

Text #16

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5919. Min Act: -0.0000

Data Index: 86887 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5762. Min Act: -0.0000

Data Index: 422527 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1351617 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5881. Min Act: -0.0000

Data Index: 15106 (The Pile)

Max Activating Token Index: 519