Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3699 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1108. Min Act: -0.0001

Data Index: 937051 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1340577 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1345016 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0973. Min Act: -0.0001

Data Index: 55311 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.1008. Min Act: -0.0001

Data Index: 531552 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0935. Min Act: -0.0001

Data Index: 789200 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0854. Min Act: -0.0001

Data Index: 928968 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0838. Min Act: -0.0001

Data Index: 898688 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1111272 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0850. Min Act: -0.0001

Data Index: 537729 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0811. Min Act: -0.0001

Data Index: 948407 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0883. Min Act: -0.0001

Data Index: 348640 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0949. Min Act: -0.0002

Data Index: 336531 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0761. Min Act: -0.0001

Data Index: 391168 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0849. Min Act: -0.0001

Data Index: 277558 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1168413 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0841. Min Act: -0.0001

Data Index: 976983 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0734. Min Act: -0.0002

Data Index: 559413 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0715. Min Act: -0.0001

Data Index: 518042 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.1108. Min Range: -0.1108

Max Act: 0.0828. Min Act: -0.0001

Data Index: 688936 (C4 (Web Text))

Max Activating Token Index: 354