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

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

Neuron 430 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0121. Min Act: -0.0005

Data Index: 812952 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0121. Min Act: -0.0005

Data Index: 950780 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0122. Min Act: -0.0005

Data Index: 502754 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1185357 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0116. Min Act: -0.0005

Data Index: 942802 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0116. Min Act: -0.0005

Data Index: 539357 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0115. Min Act: -0.0005

Data Index: 704018 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1040232 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0114. Min Act: -0.0005

Data Index: 1092869 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0112. Min Act: -0.0005

Data Index: 314170 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0110. Min Act: -0.0005

Data Index: 226115 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0111. Min Act: -0.0005

Data Index: 396739 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0110. Min Act: -0.0005

Data Index: 1249808 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1316945 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0107. Min Act: -0.0006

Data Index: 676260 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0109. Min Act: -0.0005

Data Index: 400437 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0109. Min Act: -0.0006

Data Index: 521703 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0106. Min Act: -0.0005

Data Index: 307563 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0106. Min Act: -0.0005

Data Index: 716486 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.0122. Min Range: -0.0122

Max Act: 0.0106. Min Act: -0.0005

Data Index: 141530 (C4 (Web Text))

Max Activating Token Index: 631