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

Dataset: The Pile

Neuron 3580 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: 0.8457. Min Range: -0.8457

Max Act: 0.8457. Min Act: -0.0000

Data Index: 499567 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.8356. Min Act: -0.0000

Data Index: 611955 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1559273 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7651. Min Act: -0.0000

Data Index: 863495 (The Pile)

Max Activating Token Index: 631

Text #4

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1553329 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1843413 (The Pile)

Max Activating Token Index: 559

Text #6

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6716. Min Act: -0.0000

Data Index: 685702 (The Pile)

Max Activating Token Index: 92

Text #7

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.7102. Min Act: 0.0000

Data Index: 1834746 (The Pile)

Max Activating Token Index: 434

Text #8

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1310022 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6068. Min Act: -0.0000

Data Index: 1361300 (The Pile)

Max Activating Token Index: 1018

Text #10

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.6306. Min Act: -0.0000

Data Index: 527159 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5870. Min Act: -0.0000

Data Index: 757924 (The Pile)

Max Activating Token Index: 456

Text #12

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5400. Min Act: 0.0000

Data Index: 1489487 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5886. Min Act: -0.0000

Data Index: 527514 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1705181 (The Pile)

Max Activating Token Index: 138

Text #15

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5504. Min Act: 0.0000

Data Index: 574169 (The Pile)

Max Activating Token Index: 293

Text #16

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1901545 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1613392 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.4972. Min Act: -0.0000

Data Index: 79778 (The Pile)

Max Activating Token Index: 350

Text #19

Max Range: 0.8457. Min Range: -0.8457

Max Act: 0.4918. Min Act: -0.0000

Data Index: 354781 (The Pile)

Max Activating Token Index: 1019