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

Dataset: The Pile

Neuron 1048 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1735. Min Act: -0.0000

Data Index: 190044 (The Pile)

Max Activating Token Index: 565

Text #1

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1610. Min Act: -0.0000

Data Index: 397916 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1717. Min Act: -0.0000

Data Index: 318972 (The Pile)

Max Activating Token Index: 281

Text #3

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1404. Min Act: -0.0000

Data Index: 930529 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1446. Min Act: -0.0000

Data Index: 599075 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1514752 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1338. Min Act: -0.0000

Data Index: 162004 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1228. Min Act: -0.0000

Data Index: 702784 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1228. Min Act: -0.0000

Data Index: 813370 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1117513 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1190. Min Act: -0.0000

Data Index: 1525764 (The Pile)

Max Activating Token Index: 616

Text #11

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1309. Min Act: -0.0000

Data Index: 1684625 (The Pile)

Max Activating Token Index: 802

Text #12

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1165962 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1241. Min Act: -0.0000

Data Index: 611666 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1204. Min Act: -0.0000

Data Index: 225891 (The Pile)

Max Activating Token Index: 923

Text #15

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1139. Min Act: -0.0000

Data Index: 88067 (The Pile)

Max Activating Token Index: 316

Text #16

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1956317 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1009. Min Act: -0.0000

Data Index: 154967 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1098332 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1889737 (The Pile)

Max Activating Token Index: 956