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

Dataset: The Pile

Neuron 1318 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: 0.6556. Min Range: -0.6556

Max Act: 0.6161. Min Act: -0.0000

Data Index: 969289 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1242754 (The Pile)

Max Activating Token Index: 273

Text #2

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1357785 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6523. Min Act: -0.0000

Data Index: 764766 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6168. Min Act: -0.0000

Data Index: 1320855 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1414843 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1100932 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5331. Min Act: -0.0000

Data Index: 72026 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1116972 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1550222 (The Pile)

Max Activating Token Index: 71

Text #10

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1979161 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5270. Min Act: -0.0000

Data Index: 545652 (The Pile)

Max Activating Token Index: 338

Text #12

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1143363 (The Pile)

Max Activating Token Index: 66

Text #13

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1896963 (The Pile)

Max Activating Token Index: 5

Text #14

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1889289 (The Pile)

Max Activating Token Index: 321

Text #15

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4716. Min Act: -0.0000

Data Index: 826733 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5669. Min Act: -0.0000

Data Index: 464109 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1383072 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1822496 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 0.6556. Min Range: -0.6556

Max Act: 0.5563. Min Act: -0.0000

Data Index: 1449545 (The Pile)

Max Activating Token Index: 800