Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 476 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0094. Min Act: -0.0006

Data Index: 895556 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1368663 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0093. Min Act: -0.0006

Data Index: 239703 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0088. Min Act: -0.0006

Data Index: 319392 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0092. Min Act: -0.0006

Data Index: 202083 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0092. Min Act: -0.0006

Data Index: 1303182 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0091. Min Act: -0.0006

Data Index: 230125 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0091. Min Act: -0.0005

Data Index: 462747 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1043524 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0006

Data Index: 460661 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0091. Min Act: -0.0006

Data Index: 577164 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0089. Min Act: -0.0006

Data Index: 242473 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0091. Min Act: -0.0006

Data Index: 1073555 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0087. Min Act: -0.0006

Data Index: 804886 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0088. Min Act: -0.0006

Data Index: 1161610 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0006

Data Index: 492508 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1415593 (Python Code)

Max Activating Token Index: 996

Text #17

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1285840 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0088. Min Act: -0.0006

Data Index: 799504 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0006

Data Index: 874858 (C4 (Web Text))

Max Activating Token Index: 248