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

Dataset: The Pile

Neuron 3793 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: 0.8287. Min Range: -0.8287

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1866273 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1346214 (The Pile)

Max Activating Token Index: 258

Text #2

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6483. Min Act: -0.0000

Data Index: 958217 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6053. Min Act: -0.0000

Data Index: 724759 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1219589 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1303727 (The Pile)

Max Activating Token Index: 110

Text #6

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1887706 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1847946 (The Pile)

Max Activating Token Index: 600

Text #8

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6752. Min Act: -0.0000

Data Index: 314745 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6728. Min Act: -0.0000

Data Index: 402261 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6856. Min Act: -0.0000

Data Index: 555646 (The Pile)

Max Activating Token Index: 917

Text #11

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7044. Min Act: -0.0000

Data Index: 227887 (The Pile)

Max Activating Token Index: 449

Text #12

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6992. Min Act: -0.0000

Data Index: 420789 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1519645 (The Pile)

Max Activating Token Index: 736

Text #14

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6569. Min Act: -0.0000

Data Index: 202331 (The Pile)

Max Activating Token Index: 782

Text #15

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6481. Min Act: -0.0000

Data Index: 217924 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6598. Min Act: -0.0000

Data Index: 907740 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1075457 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.7137. Min Act: -0.0000

Data Index: 87756 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.8287. Min Range: -0.8287

Max Act: 0.6272. Min Act: -0.0000

Data Index: 548825 (The Pile)

Max Activating Token Index: 185