Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 474 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0018. Min Act: -0.0002

Data Index: 576911 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0015. Min Act: -0.0002

Data Index: 1606716 (Python Code)

Max Activating Token Index: 166

Text #2

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0013. Min Act: -0.0002

Data Index: 343574 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0013. Min Act: -0.0003

Data Index: 1147017 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0013. Min Act: -0.0002

Data Index: 1077075 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0013. Min Act: -0.0002

Data Index: 1642495 (Python Code)

Max Activating Token Index: 735

Text #6

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1526131 (Python Code)

Max Activating Token Index: 561

Text #7

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0013. Min Act: -0.0002

Data Index: 1308292 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1130876 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0012. Min Act: -0.0002

Data Index: 450136 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0012. Min Act: -0.0002

Data Index: 193187 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0002

Data Index: 928657 (C4 (Web Text))

Max Activating Token Index: 217

Text #12

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0002

Data Index: 436726 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1455117 (Python Code)

Max Activating Token Index: 741

Text #14

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0003

Data Index: 95238 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1247937 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1351411 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1114436 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1012519 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.0018. Min Range: -0.0018

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1417269 (Python Code)

Max Activating Token Index: 651