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

Dataset: The Pile

Neuron 3110 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1246619 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1495720 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1375025 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1978625 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1538023 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4971. Min Act: -0.0000

Data Index: 482433 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4798. Min Act: -0.0000

Data Index: 1838518 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4178. Min Act: -0.0000

Data Index: 556233 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4720. Min Act: -0.0000

Data Index: 265525 (The Pile)

Max Activating Token Index: 281

Text #9

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1437046 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4396. Min Act: -0.0000

Data Index: 181971 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1801459 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4326. Min Act: -0.0000

Data Index: 621440 (The Pile)

Max Activating Token Index: 44

Text #13

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1696701 (The Pile)

Max Activating Token Index: 117

Text #14

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1788848 (The Pile)

Max Activating Token Index: 406

Text #15

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1314771 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1095139 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4464. Min Act: -0.0000

Data Index: 346591 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1705826 (The Pile)

Max Activating Token Index: 521

Text #19

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4776. Min Act: -0.0000

Data Index: 866946 (The Pile)

Max Activating Token Index: 261