Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1754 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1259218 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0952. Min Act: -0.0002

Data Index: 200296 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0915. Min Act: -0.0002

Data Index: 775080 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0871. Min Act: -0.0002

Data Index: 669769 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1212663 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0871. Min Act: -0.0002

Data Index: 387199 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1056993 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0897. Min Act: -0.0002

Data Index: 516627 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0904. Min Act: -0.0002

Data Index: 386686 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1345715 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0864. Min Act: -0.0002

Data Index: 430274 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0859. Min Act: -0.0002

Data Index: 205794 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0796. Min Act: -0.0002

Data Index: 716457 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1093151 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0925. Min Act: -0.0002

Data Index: 552760 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1338882 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1275718 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0879. Min Act: -0.0002

Data Index: 1056236 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1312330 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 0.0952. Min Range: -0.0952

Max Act: 0.0873. Min Act: -0.0002

Data Index: 841336 (C4 (Web Text))

Max Activating Token Index: 667