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

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

Neuron 345 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: 0.0071. Min Range: -0.0071

Max Act: 0.0071. Min Act: -0.0005

Data Index: 93742 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0070. Min Act: -0.0006

Data Index: 47730 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0064. Min Act: -0.0006

Data Index: 349831 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0005

Data Index: 1446539 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0006

Data Index: 262294 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0006

Data Index: 120727 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0063. Min Act: -0.0006

Data Index: 798445 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0060. Min Act: -0.0006

Data Index: 102174 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1580645 (Python Code)

Max Activating Token Index: 999

Text #9

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0059. Min Act: -0.0005

Data Index: 1158180 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1255574 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0059. Min Act: -0.0006

Data Index: 128039 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0059. Min Act: -0.0006

Data Index: 829185 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1261152 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1245156 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1092952 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1058528 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0060. Min Act: -0.0006

Data Index: 925611 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1354261 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0071. Min Range: -0.0071

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1555169 (Python Code)

Max Activating Token Index: 970