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

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

Neuron 1974 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: 0.0050. Min Range: -0.0050

Max Act: 0.0050. Min Act: -0.0006

Data Index: 1112464 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1098487 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0044. Min Act: -0.0006

Data Index: 694072 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0038. Min Act: -0.0005

Data Index: 767593 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0036. Min Act: -0.0005

Data Index: 89716 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0033. Min Act: -0.0006

Data Index: 1194646 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0032. Min Act: -0.0005

Data Index: 52811 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0031. Min Act: -0.0005

Data Index: 240675 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0031. Min Act: -0.0006

Data Index: 147182 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0030. Min Act: -0.0005

Data Index: 158798 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1241416 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0029. Min Act: -0.0005

Data Index: 974282 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0028. Min Act: -0.0005

Data Index: 334538 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0028. Min Act: -0.0005

Data Index: 287719 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0028. Min Act: -0.0006

Data Index: 391779 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0029. Min Act: -0.0006

Data Index: 345732 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0029. Min Act: -0.0006

Data Index: 324279 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0028. Min Act: -0.0005

Data Index: 722044 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0027. Min Act: -0.0006

Data Index: 965723 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.0050. Min Range: -0.0050

Max Act: 0.0027. Min Act: -0.0006

Data Index: 243910 (C4 (Web Text))

Max Activating Token Index: 601