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

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

Neuron 4354 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.5063. Min Act: -0.0000

Data Index: 100799 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.3834. Min Act: -0.0000

Data Index: 366287 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.5373. Min Act: -0.0000

Data Index: 593405 (C4 (Web Text))

Max Activating Token Index: 668

Text #3

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.0857. Min Act: -0.0000

Data Index: 735778 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.0870. Min Act: -0.0000

Data Index: 821378 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1109413 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1051603 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.0050. Min Act: -0.0000

Data Index: 1051569 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.8999. Min Act: -0.0000

Data Index: 562082 (C4 (Web Text))

Max Activating Token Index: 241

Text #9

Max Range: 1.5373. Min Range: -1.5373

Max Act: 1.0232. Min Act: -0.0000

Data Index: 1089714 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1258563 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.9785. Min Act: -0.0000

Data Index: 1024785 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.8796. Min Act: -0.0000

Data Index: 1053411 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.8854. Min Act: -0.0000

Data Index: 756105 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.7187. Min Act: -0.0000

Data Index: 588441 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.7729. Min Act: -0.0000

Data Index: 322118 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1171801 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.7875. Min Act: -0.0000

Data Index: 114824 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1051215 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 1.5373. Min Range: -1.5373

Max Act: 0.7293. Min Act: -0.0000

Data Index: 239730 (C4 (Web Text))

Max Activating Token Index: 692