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

Dataset: The Pile

Neuron 2234 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1815. Min Range: -1.1815

Max Act: 1.1815. Min Act: -0.0000

Data Index: 506940 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 1.1815. Min Range: -1.1815

Max Act: 1.1776. Min Act: -0.0000

Data Index: 887013 (The Pile)

Max Activating Token Index: 556

Text #2

Max Range: 1.1815. Min Range: -1.1815

Max Act: 1.1733. Min Act: -0.0000

Data Index: 1036245 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 1.1815. Min Range: -1.1815

Max Act: 1.0601. Min Act: -0.0000

Data Index: 372768 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9719. Min Act: -0.0000

Data Index: 294128 (The Pile)

Max Activating Token Index: 746

Text #5

Max Range: 1.1815. Min Range: -1.1815

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1433374 (The Pile)

Max Activating Token Index: 567

Text #6

Max Range: 1.1815. Min Range: -1.1815

Max Act: 1.0570. Min Act: -0.0000

Data Index: 419452 (The Pile)

Max Activating Token Index: 484

Text #7

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9943. Min Act: -0.0000

Data Index: 998824 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9841. Min Act: -0.0000

Data Index: 585777 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9725. Min Act: -0.0000

Data Index: 821606 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9713. Min Act: -0.0000

Data Index: 239852 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9302. Min Act: -0.0000

Data Index: 488100 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 1.1815. Min Range: -1.1815

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1131228 (The Pile)

Max Activating Token Index: 228

Text #13

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1854767 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9641. Min Act: -0.0000

Data Index: 443931 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9627. Min Act: -0.0000

Data Index: 616232 (The Pile)

Max Activating Token Index: 118

Text #16

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9518. Min Act: -0.0000

Data Index: 458325 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1795769 (The Pile)

Max Activating Token Index: 322

Text #18

Max Range: 1.1815. Min Range: -1.1815

Max Act: 0.9535. Min Act: -0.0000

Data Index: 643934 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 1.1815. Min Range: -1.1815

Max Act: 1.0460. Min Act: -0.0000

Data Index: 327299 (The Pile)

Max Activating Token Index: 905