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

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

Neuron 1613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.7095. Min Act: -0.0000

Data Index: 305114 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.6502. Min Act: -0.0000

Data Index: 362351 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.6195. Min Act: -0.0000

Data Index: 224434 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.6052. Min Act: -0.0000

Data Index: 179896 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5847. Min Act: -0.0000

Data Index: 1131168 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5312. Min Act: -0.0000

Data Index: 38117 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5393. Min Act: -0.0000

Data Index: 928079 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5520. Min Act: -0.0000

Data Index: 388492 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1608612 (Python Code)

Max Activating Token Index: 946

Text #9

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1426703 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5568. Min Act: -0.0000

Data Index: 687162 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5607. Min Act: -0.0000

Data Index: 911654 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5191. Min Act: -0.0000

Data Index: 720763 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1524014 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5109. Min Act: -0.0000

Data Index: 883227 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5448. Min Act: -0.0000

Data Index: 1481764 (Python Code)

Max Activating Token Index: 922

Text #16

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5163. Min Act: -0.0000

Data Index: 109693 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.5035. Min Act: -0.0000

Data Index: 156915 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4859. Min Act: -0.0000

Data Index: 260434 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.7095. Min Range: -0.7095

Max Act: 0.4926. Min Act: -0.0000

Data Index: 898103 (C4 (Web Text))

Max Activating Token Index: 723