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

Dataset: The Pile

Neuron 1777 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1797442 (The Pile)

Max Activating Token Index: 508

Text #1

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1243516 (The Pile)

Max Activating Token Index: 241

Text #2

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1587976 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1644271 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1237285 (The Pile)

Max Activating Token Index: 831

Text #5

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.6465. Min Act: -0.0000

Data Index: 235033 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5491. Min Act: -0.0000

Data Index: 968968 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5990. Min Act: -0.0000

Data Index: 258750 (The Pile)

Max Activating Token Index: 290

Text #8

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5644. Min Act: -0.0000

Data Index: 735113 (The Pile)

Max Activating Token Index: 523

Text #9

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1521800 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5642. Min Act: -0.0000

Data Index: 976030 (The Pile)

Max Activating Token Index: 49

Text #11

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5478. Min Act: -0.0000

Data Index: 580137 (The Pile)

Max Activating Token Index: 125

Text #12

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5674. Min Act: -0.0000

Data Index: 426921 (The Pile)

Max Activating Token Index: 474

Text #13

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5028. Min Act: -0.0000

Data Index: 1449245 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.4358. Min Act: -0.0000

Data Index: 621716 (The Pile)

Max Activating Token Index: 656

Text #15

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1131583 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1633895 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5202. Min Act: -0.0000

Data Index: 469401 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5304. Min Act: -0.0000

Data Index: 752450 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1543988 (The Pile)

Max Activating Token Index: 57