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

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

Neuron 4778 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: 0.0123. Min Range: -0.0123

Max Act: 0.0123. Min Act: -0.0001

Data Index: 1518094 (Python Code)

Max Activating Token Index: 626

Text #1

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0109. Min Act: -0.0001

Data Index: 57766 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0094. Min Act: -0.0001

Data Index: 699954 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0096. Min Act: -0.0001

Data Index: 140797 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0097. Min Act: -0.0001

Data Index: 603544 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0092. Min Act: -0.0000

Data Index: 1015163 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0100. Min Act: -0.0000

Data Index: 434840 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0092. Min Act: -0.0001

Data Index: 7041 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0088. Min Act: -0.0000

Data Index: 774183 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0088. Min Act: -0.0000

Data Index: 890728 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0088. Min Act: -0.0001

Data Index: 567256 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0089. Min Act: -0.0001

Data Index: 786497 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0086. Min Act: -0.0001

Data Index: 1277597 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0085. Min Act: -0.0001

Data Index: 192746 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0088. Min Act: -0.0000

Data Index: 1135064 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0086. Min Act: -0.0001

Data Index: 471773 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0078. Min Act: -0.0000

Data Index: 214423 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0086. Min Act: -0.0001

Data Index: 739382 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0087. Min Act: -0.0001

Data Index: 610468 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.0123. Min Range: -0.0123

Max Act: 0.0080. Min Act: -0.0001

Data Index: 53857 (C4 (Web Text))

Max Activating Token Index: 374