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

Dataset: The Pile

Neuron 14 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: 0.7982. Min Range: -0.7982

Max Act: 0.7982. Min Act: -0.0000

Data Index: 793830 (The Pile)

Max Activating Token Index: 403

Text #1

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1692756 (The Pile)

Max Activating Token Index: 444

Text #2

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7360. Min Act: -0.0000

Data Index: 414910 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7278. Min Act: -0.0000

Data Index: 949575 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1885736 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1659861 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1207799 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1624009 (The Pile)

Max Activating Token Index: 462

Text #8

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6233. Min Act: -0.0000

Data Index: 383134 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1400891 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6425. Min Act: -0.0000

Data Index: 229342 (The Pile)

Max Activating Token Index: 273

Text #11

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6214. Min Act: -0.0000

Data Index: 583826 (The Pile)

Max Activating Token Index: 600

Text #12

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6497. Min Act: -0.0000

Data Index: 599409 (The Pile)

Max Activating Token Index: 94

Text #13

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6101. Min Act: -0.0000

Data Index: 705910 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6426. Min Act: -0.0000

Data Index: 429902 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6394. Min Act: -0.0000

Data Index: 811961 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1537592 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1151531 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6109. Min Act: -0.0000

Data Index: 123922 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5799. Min Act: -0.0000

Data Index: 529096 (The Pile)

Max Activating Token Index: 570