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

Dataset: The Pile

Neuron 4194 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.6212. Min Act: -0.0000

Data Index: 102822 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.6583. Min Act: -0.0000

Data Index: 908687 (The Pile)

Max Activating Token Index: 643

Text #2

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1359362 (The Pile)

Max Activating Token Index: 961

Text #3

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4358. Min Act: -0.0000

Data Index: 503881 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.4207. Min Act: -0.0000

Data Index: 441505 (The Pile)

Max Activating Token Index: 362

Text #5

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.3872. Min Act: -0.0000

Data Index: 1919404 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1245071 (The Pile)

Max Activating Token Index: 864

Text #7

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.3202. Min Act: -0.0000

Data Index: 175231 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1090595 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1415073 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.3250. Min Act: -0.0000

Data Index: 231666 (The Pile)

Max Activating Token Index: 592

Text #11

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1425010 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.2851. Min Act: -0.0000

Data Index: 4079 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1675748 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1694853 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.2894. Min Act: -0.0000

Data Index: 970479 (The Pile)

Max Activating Token Index: 63

Text #16

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1782084 (The Pile)

Max Activating Token Index: 985

Text #17

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1269299 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1388807 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 0.6583. Min Range: -0.6583

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1123984 (The Pile)

Max Activating Token Index: 723