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

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

Neuron 3433 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.9546. Min Act: -0.0000

Data Index: 1157615 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.8683. Min Act: -0.0000

Data Index: 192886 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.7374. Min Act: -0.0000

Data Index: 1151779 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.6869. Min Act: -0.0001

Data Index: 1148172 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.6903. Min Act: -0.0000

Data Index: 595482 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.8319. Min Act: -0.0000

Data Index: 519682 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.6073. Min Act: -0.0000

Data Index: 700974 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1171631 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.5638. Min Act: -0.0001

Data Index: 604983 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.5010. Min Act: -0.0000

Data Index: 1125342 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.6522. Min Act: -0.0001

Data Index: 1296546 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.4711. Min Act: -0.0000

Data Index: 111713 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.6098. Min Act: -0.0000

Data Index: 233515 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.4243. Min Act: -0.0000

Data Index: 1276364 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.4975. Min Act: -0.0000

Data Index: 508097 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.3662. Min Act: -0.0000

Data Index: 493950 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.3609. Min Act: -0.0001

Data Index: 18685 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.5150. Min Act: -0.0000

Data Index: 1287899 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1087012 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 1.9546. Min Range: -1.9546

Max Act: 1.3814. Min Act: -0.0001

Data Index: 881833 (C4 (Web Text))

Max Activating Token Index: 160