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

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

Neuron 4402 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: 1.0074. Min Range: -1.0074

Max Act: 1.0074. Min Act: -0.0000

Data Index: 948616 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.8139. Min Act: -0.0000

Data Index: 687189 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.8689. Min Act: -0.0000

Data Index: 519944 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1268825 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.8565. Min Act: -0.0000

Data Index: 131289 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.8031. Min Act: -0.0000

Data Index: 44377 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.8783. Min Act: -0.0000

Data Index: 996455 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7184. Min Act: -0.0000

Data Index: 422481 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7514. Min Act: -0.0000

Data Index: 727916 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7495. Min Act: -0.0000

Data Index: 885720 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7345. Min Act: -0.0000

Data Index: 19048 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7298. Min Act: -0.0000

Data Index: 83636 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7841. Min Act: -0.0000

Data Index: 812118 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7088. Min Act: -0.0000

Data Index: 275911 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7121. Min Act: -0.0000

Data Index: 82891 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1318314 (C4 (Web Text))

Max Activating Token Index: 770

Text #16

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1200849 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1168081 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6854. Min Act: -0.0000

Data Index: 487643 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.0074. Min Range: -1.0074

Max Act: 0.6821. Min Act: -0.0000

Data Index: 37002 (C4 (Web Text))

Max Activating Token Index: 602