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

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

Neuron 3534 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7653. Min Range: -2.7653

Max Act: 2.7653. Min Act: -0.0000

Data Index: 35097 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 2.7653. Min Range: -2.7653

Max Act: 2.3105. Min Act: -0.0000

Data Index: 750503 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.7768. Min Act: -0.0000

Data Index: 102069 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 2.7653. Min Range: -2.7653

Max Act: 2.0943. Min Act: -0.0000

Data Index: 252732 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.9363. Min Act: -0.0000

Data Index: 227825 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.9023. Min Act: -0.0000

Data Index: 1292597 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.5756. Min Act: -0.0000

Data Index: 1349915 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.8694. Min Act: -0.0000

Data Index: 1188657 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.8539. Min Act: -0.0000

Data Index: 683317 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.7375. Min Act: -0.0000

Data Index: 348268 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.7615. Min Act: -0.0000

Data Index: 440795 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.8200. Min Act: -0.0000

Data Index: 441111 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.7373. Min Act: -0.0000

Data Index: 888490 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.5246. Min Act: -0.0000

Data Index: 557400 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.7227. Min Act: -0.0000

Data Index: 107177 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.7073. Min Act: -0.0000

Data Index: 372096 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.4395. Min Act: -0.0000

Data Index: 312897 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.5999. Min Act: -0.0000

Data Index: 930001 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.6356. Min Act: -0.0000

Data Index: 475931 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 2.7653. Min Range: -2.7653

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1213594 (C4 (Web Text))

Max Activating Token Index: 148