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

Dataset: The Pile

Neuron 4689 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: 0.7036. Min Range: -0.7036

Max Act: 0.7036. Min Act: -0.0000

Data Index: 522697 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1012813 (The Pile)

Max Activating Token Index: 452

Text #2

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6619. Min Act: -0.0000

Data Index: 1424788 (The Pile)

Max Activating Token Index: 86

Text #3

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1897279 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1085809 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.6274. Min Act: -0.0000

Data Index: 389903 (The Pile)

Max Activating Token Index: 326

Text #6

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1344786 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5710. Min Act: -0.0000

Data Index: 624159 (The Pile)

Max Activating Token Index: 102

Text #8

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1376211 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5208. Min Act: -0.0000

Data Index: 796523 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5310. Min Act: -0.0000

Data Index: 585595 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.3986. Min Act: -0.0000

Data Index: 748617 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1674437 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1616751 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5128. Min Act: -0.0000

Data Index: 710036 (The Pile)

Max Activating Token Index: 373

Text #15

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1133547 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.4877. Min Act: -0.0000

Data Index: 255699 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1779258 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.5548. Min Act: -0.0000

Data Index: 1271439 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 0.7036. Min Range: -0.7036

Max Act: 0.3672. Min Act: -0.0000

Data Index: 526090 (The Pile)

Max Activating Token Index: 1016