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

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

Neuron 4915 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.1153. Min Act: 0.0000

Data Index: 1516466 (Python Code)

Max Activating Token Index: 324

Text #1

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.2029. Min Act: -0.0000

Data Index: 708988 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0565. Min Act: -0.0000

Data Index: 1330611 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1164483 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9612. Min Act: -0.0000

Data Index: 337258 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 1.2029. Min Range: -1.2029

Max Act: 1.0184. Min Act: -0.0000

Data Index: 275168 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1652078 (Python Code)

Max Activating Token Index: 659

Text #7

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1494561 (Python Code)

Max Activating Token Index: 766

Text #8

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1595264 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9087. Min Act: -0.0000

Data Index: 389586 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1486870 (Python Code)

Max Activating Token Index: 861

Text #11

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8416. Min Act: -0.0000

Data Index: 438860 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8128. Min Act: -0.0000

Data Index: 807502 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1593481 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1420007 (Python Code)

Max Activating Token Index: 127

Text #15

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9088. Min Act: 0.0000

Data Index: 1448402 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1620061 (Python Code)

Max Activating Token Index: 881

Text #17

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1587059 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8504. Min Act: -0.0000

Data Index: 645186 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 1.2029. Min Range: -1.2029

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1382252 (Python Code)

Max Activating Token Index: 347