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

Dataset: The Pile

Neuron 3172 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: 0.3432. Min Range: -0.3432

Max Act: 0.3245. Min Act: -0.0000

Data Index: 995904 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3432. Min Act: -0.0000

Data Index: 258487 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3182. Min Act: -0.0000

Data Index: 700360 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3279. Min Act: -0.0000

Data Index: 84810 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1348014 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1265586 (The Pile)

Max Activating Token Index: 867

Text #6

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3135. Min Act: -0.0000

Data Index: 854448 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3057. Min Act: -0.0000

Data Index: 564609 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2907. Min Act: -0.0000

Data Index: 439490 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2803. Min Act: -0.0000

Data Index: 145352 (The Pile)

Max Activating Token Index: 860

Text #10

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.3112. Min Act: -0.0000

Data Index: 812113 (The Pile)

Max Activating Token Index: 927

Text #11

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1130548 (The Pile)

Max Activating Token Index: 500

Text #12

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2861. Min Act: -0.0000

Data Index: 653455 (The Pile)

Max Activating Token Index: 556

Text #13

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2538. Min Act: -0.0000

Data Index: 821757 (The Pile)

Max Activating Token Index: 424

Text #14

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1015946 (The Pile)

Max Activating Token Index: 760

Text #15

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2725. Min Act: -0.0000

Data Index: 285847 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2628. Min Act: -0.0000

Data Index: 826086 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2886. Min Act: -0.0000

Data Index: 812124 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1346845 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.3432. Min Range: -0.3432

Max Act: 0.2664. Min Act: -0.0000

Data Index: 344737 (The Pile)

Max Activating Token Index: 697