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

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

Neuron 3426 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1360693 (Python Code)

Max Activating Token Index: 816

Text #1

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1132232 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0132. Min Act: -0.0002

Data Index: 83835 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0130. Min Act: -0.0002

Data Index: 845115 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1011000 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0129. Min Act: -0.0002

Data Index: 906949 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0132. Min Act: -0.0002

Data Index: 767392 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0128. Min Act: -0.0002

Data Index: 864523 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0122. Min Act: -0.0002

Data Index: 73637 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0127. Min Act: -0.0002

Data Index: 134208 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1036631 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1115236 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0121. Min Act: -0.0002

Data Index: 1518871 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1159652 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1007053 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0117. Min Act: -0.0002

Data Index: 727552 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0118. Min Act: -0.0002

Data Index: 209916 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0116. Min Act: -0.0002

Data Index: 207635 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0116. Min Act: -0.0002

Data Index: 139325 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.0207. Min Range: -0.0207

Max Act: 0.0116. Min Act: -0.0002

Data Index: 348390 (C4 (Web Text))

Max Activating Token Index: 490