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

Dataset: The Pile

Neuron 628 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.8918. Min Act: -0.0000

Data Index: 504565 (The Pile)

Max Activating Token Index: 185

Text #1

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.7256. Min Act: -0.0000

Data Index: 628350 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.6742. Min Act: -0.0000

Data Index: 313647 (The Pile)

Max Activating Token Index: 16

Text #3

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.6719. Min Act: -0.0000

Data Index: 1072909 (The Pile)

Max Activating Token Index: 1017

Text #4

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.7375. Min Act: -0.0000

Data Index: 963661 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.6402. Min Act: -0.0000

Data Index: 1333278 (The Pile)

Max Activating Token Index: 1012

Text #6

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1272680 (The Pile)

Max Activating Token Index: 975

Text #7

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.5609. Min Act: -0.0000

Data Index: 1784554 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.3727. Min Act: -0.0000

Data Index: 1654952 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.4060. Min Act: -0.0000

Data Index: 1148687 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.3307. Min Act: -0.0000

Data Index: 380521 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.4628. Min Act: -0.0000

Data Index: 1231611 (The Pile)

Max Activating Token Index: 815

Text #12

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.4441. Min Act: -0.0000

Data Index: 1236034 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1020526 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.4939. Min Act: -0.0000

Data Index: 1590509 (The Pile)

Max Activating Token Index: 963

Text #15

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.3206. Min Act: -0.0000

Data Index: 1790348 (The Pile)

Max Activating Token Index: 741

Text #16

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1297283 (The Pile)

Max Activating Token Index: 519

Text #17

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.3818. Min Act: -0.0000

Data Index: 1153398 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.3574. Min Act: -0.0000

Data Index: 186708 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 1.8918. Min Range: -1.8918

Max Act: 1.4419. Min Act: -0.0000

Data Index: 29039 (The Pile)

Max Activating Token Index: 148