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

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

Neuron 526 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0663. Min Act: -0.0001

Data Index: 1585562 (Python Code)

Max Activating Token Index: 641

Text #1

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.2003. Min Act: -0.0001

Data Index: 1426517 (Python Code)

Max Activating Token Index: 266

Text #2

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0185. Min Act: -0.0001

Data Index: 1340642 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9427. Min Act: -0.0001

Data Index: 1219697 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9963. Min Act: -0.0001

Data Index: 958046 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.2003. Min Range: -1.2003

Max Act: 1.0878. Min Act: -0.0001

Data Index: 1518344 (Python Code)

Max Activating Token Index: 698

Text #6

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9085. Min Act: -0.0001

Data Index: 886087 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9401. Min Act: -0.0001

Data Index: 708860 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9553. Min Act: -0.0001

Data Index: 405258 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.8973. Min Act: -0.0001

Data Index: 1207302 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.8689. Min Act: -0.0001

Data Index: 1440028 (Python Code)

Max Activating Token Index: 979

Text #11

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9383. Min Act: -0.0001

Data Index: 312518 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9643. Min Act: -0.0001

Data Index: 1068014 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9620. Min Act: -0.0001

Data Index: 1194395 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.8746. Min Act: -0.0001

Data Index: 1487552 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.8814. Min Act: -0.0001

Data Index: 1636258 (Python Code)

Max Activating Token Index: 495

Text #16

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.7779. Min Act: -0.0001

Data Index: 1530665 (Python Code)

Max Activating Token Index: 520

Text #17

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9135. Min Act: -0.0001

Data Index: 232175 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.9338. Min Act: -0.0001

Data Index: 1535540 (Python Code)

Max Activating Token Index: 144

Text #19

Max Range: 1.2003. Min Range: -1.2003

Max Act: 0.8718. Min Act: -0.0001

Data Index: 1528651 (Python Code)

Max Activating Token Index: 573