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

Dataset: The Pile

Neuron 106 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7585. Min Range: -5.7585

Max Act: 5.1612. Min Act: -0.0000

Data Index: 969772 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 5.7585. Min Range: -5.7585

Max Act: 5.7585. Min Act: -0.0000

Data Index: 927674 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 5.7585. Min Range: -5.7585

Max Act: 5.6191. Min Act: -0.0000

Data Index: 1664173 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.6988. Min Act: -0.0000

Data Index: 651691 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.7730. Min Act: -0.0000

Data Index: 334940 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.5768. Min Act: -0.0000

Data Index: 1448902 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.5625. Min Act: -0.0000

Data Index: 1259863 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.7909. Min Act: -0.0000

Data Index: 62756 (The Pile)

Max Activating Token Index: 647

Text #8

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.5379. Min Act: -0.0000

Data Index: 1410634 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.4356. Min Act: -0.0000

Data Index: 850541 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.3244. Min Act: -0.0000

Data Index: 1953537 (The Pile)

Max Activating Token Index: 974

Text #11

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.6546. Min Act: -0.0000

Data Index: 680578 (The Pile)

Max Activating Token Index: 415

Text #12

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.1142. Min Act: -0.0000

Data Index: 447059 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.3173. Min Act: -0.0000

Data Index: 773272 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.2799. Min Act: -0.0000

Data Index: 1458880 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.1543. Min Act: -0.0000

Data Index: 1035431 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.4687. Min Act: -0.0000

Data Index: 88178 (The Pile)

Max Activating Token Index: 548

Text #17

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.0913. Min Act: -0.0000

Data Index: 80052 (The Pile)

Max Activating Token Index: 757

Text #18

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.2168. Min Act: -0.0000

Data Index: 1567374 (The Pile)

Max Activating Token Index: 310

Text #19

Max Range: 5.7585. Min Range: -5.7585

Max Act: 4.3097. Min Act: -0.0000

Data Index: 292174 (The Pile)

Max Activating Token Index: 409