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

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

Neuron 3641 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1096. Min Act: -0.0003

Data Index: 551062 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0986. Min Act: -0.0003

Data Index: 168603 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0972. Min Act: -0.0003

Data Index: 452225 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0903. Min Act: -0.0003

Data Index: 204303 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0849. Min Act: -0.0003

Data Index: 749276 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0906. Min Act: -0.0003

Data Index: 662013 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0862. Min Act: -0.0003

Data Index: 1327854 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0813. Min Act: -0.0003

Data Index: 121268 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0759. Min Act: -0.0003

Data Index: 646398 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0792. Min Act: -0.0003

Data Index: 580286 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0781. Min Act: -0.0003

Data Index: 154950 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0734. Min Act: -0.0003

Data Index: 38816 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0708. Min Act: -0.0003

Data Index: 124079 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0726. Min Act: -0.0003

Data Index: 565279 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1125758 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0705. Min Act: -0.0002

Data Index: 551063 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1309754 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0661. Min Act: -0.0003

Data Index: 917676 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0668. Min Act: -0.0002

Data Index: 837801 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0676. Min Act: -0.0003

Data Index: 492096 (C4 (Web Text))

Max Activating Token Index: 66