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

Dataset: The Pile

Neuron 437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.6223. Min Act: -0.0000

Data Index: 1200762 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5281. Min Act: -0.0000

Data Index: 1947552 (The Pile)

Max Activating Token Index: 868

Text #2

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5341. Min Act: -0.0000

Data Index: 433583 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.5336. Min Act: -0.0000

Data Index: 1863950 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.6252. Min Act: -0.0000

Data Index: 1112088 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1304251 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.2331. Min Act: -0.0000

Data Index: 577760 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.3774. Min Act: -0.0000

Data Index: 1907868 (The Pile)

Max Activating Token Index: 917

Text #8

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.1830. Min Act: -0.0000

Data Index: 1528407 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9916. Min Act: -0.0001

Data Index: 766795 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.1007. Min Act: -0.0000

Data Index: 297937 (The Pile)

Max Activating Token Index: 573

Text #11

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.1001. Min Act: -0.0000

Data Index: 896823 (The Pile)

Max Activating Token Index: 811

Text #12

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9620. Min Act: -0.0000

Data Index: 408299 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1281843 (The Pile)

Max Activating Token Index: 434

Text #14

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.7462. Min Act: -0.0000

Data Index: 661550 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9889. Min Act: -0.0000

Data Index: 1314805 (The Pile)

Max Activating Token Index: 504

Text #16

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1589441 (The Pile)

Max Activating Token Index: 166

Text #17

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.9782. Min Act: -0.0000

Data Index: 1634279 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 1.6252. Min Range: -1.6252

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1958176 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 1.6252. Min Range: -1.6252

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1617216 (The Pile)

Max Activating Token Index: 447