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

Dataset: The Pile

Neuron 583 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7512. Min Act: -0.0000

Data Index: 46892 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1319517 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1489576 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6085. Min Act: -0.0000

Data Index: 664199 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1277638 (The Pile)

Max Activating Token Index: 934

Text #5

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5695. Min Act: -0.0000

Data Index: 326300 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5733. Min Act: 0.0000

Data Index: 130024 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5355. Min Act: -0.0000

Data Index: 336765 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5229. Min Act: -0.0000

Data Index: 744334 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5394. Min Act: -0.0000

Data Index: 1050205 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5789. Min Act: -0.0000

Data Index: 63918 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5110. Min Act: -0.0000

Data Index: 310584 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1446293 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5330. Min Act: -0.0000

Data Index: 396260 (The Pile)

Max Activating Token Index: 474

Text #14

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5325. Min Act: -0.0000

Data Index: 76467 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1426382 (The Pile)

Max Activating Token Index: 410

Text #16

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1270002 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1503192 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.4986. Min Act: -0.0000

Data Index: 476354 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1741007 (The Pile)

Max Activating Token Index: 264