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

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

Neuron 433 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: 0.0127. Min Range: -0.0127

Max Act: 0.0127. Min Act: -0.0006

Data Index: 295788 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0108. Min Act: -0.0006

Data Index: 614500 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1001454 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1036080 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0108. Min Act: -0.0006

Data Index: 1278101 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0102. Min Act: -0.0006

Data Index: 866352 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0107. Min Act: -0.0005

Data Index: 1137142 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1463663 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1285226 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1091130 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0102. Min Act: -0.0006

Data Index: 816934 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1200286 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1576751 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0103. Min Act: -0.0006

Data Index: 47693 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0099. Min Act: -0.0006

Data Index: 56007 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0101. Min Act: -0.0006

Data Index: 195261 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0098. Min Act: -0.0005

Data Index: 147321 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0101. Min Act: -0.0006

Data Index: 835955 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0100. Min Act: -0.0006

Data Index: 480005 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.0127. Min Range: -0.0127

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1654232 (Python Code)

Max Activating Token Index: 565