Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1213 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0836. Min Range: -1.0836

Max Act: 1.0836. Min Act: -0.0002

Data Index: 119285 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.9495. Min Act: -0.0002

Data Index: 798457 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8785. Min Act: -0.0002

Data Index: 90553 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8902. Min Act: -0.0002

Data Index: 193708 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8803. Min Act: -0.0002

Data Index: 367664 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7706. Min Act: -0.0002

Data Index: 614082 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7935. Min Act: -0.0002

Data Index: 401270 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7557. Min Act: -0.0002

Data Index: 94542 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7908. Min Act: -0.0002

Data Index: 30039 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7494. Min Act: -0.0002

Data Index: 677654 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.8649. Min Act: -0.0002

Data Index: 811539 (C4 (Web Text))

Max Activating Token Index: 135

Text #11

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7393. Min Act: -0.0002

Data Index: 278811 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7185. Min Act: -0.0002

Data Index: 226553 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7609. Min Act: -0.0002

Data Index: 201580 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7565. Min Act: -0.0002

Data Index: 564191 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7094. Min Act: -0.0002

Data Index: 1385412 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6982. Min Act: -0.0002

Data Index: 786446 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6879. Min Act: -0.0002

Data Index: 137575 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.7077. Min Act: -0.0002

Data Index: 619341 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 1.0836. Min Range: -1.0836

Max Act: 0.6963. Min Act: -0.0002

Data Index: 413037 (C4 (Web Text))

Max Activating Token Index: 376