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

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

Neuron 2535 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2923. Min Range: -2.2923

Max Act: 2.2923. Min Act: -0.0001

Data Index: 890935 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.9800. Min Act: -0.0000

Data Index: 572957 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.9094. Min Act: -0.0000

Data Index: 900442 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.7249. Min Act: -0.0000

Data Index: 171243 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.8145. Min Act: -0.0001

Data Index: 1312677 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.8831. Min Act: -0.0000

Data Index: 510861 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.7744. Min Act: -0.0000

Data Index: 394046 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.8096. Min Act: -0.0001

Data Index: 713426 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.7736. Min Act: -0.0000

Data Index: 405915 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.7429. Min Act: -0.0000

Data Index: 139547 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.7304. Min Act: -0.0000

Data Index: 1144075 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.6206. Min Act: -0.0000

Data Index: 1170204 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.7109. Min Act: -0.0000

Data Index: 1275151 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.6816. Min Act: -0.0000

Data Index: 1136177 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.6712. Min Act: -0.0000

Data Index: 582689 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.8069. Min Act: -0.0001

Data Index: 1030729 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.6549. Min Act: -0.0001

Data Index: 642844 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.5671. Min Act: -0.0001

Data Index: 1253473 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.5972. Min Act: -0.0001

Data Index: 244177 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 2.2923. Min Range: -2.2923

Max Act: 1.6422. Min Act: -0.0001

Data Index: 340353 (C4 (Web Text))

Max Activating Token Index: 174