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

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

Neuron 3360 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0095. Min Range: -2.0095

Max Act: 2.0094. Min Act: -0.0000

Data Index: 868393 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 2.0095. Min Range: -2.0095

Max Act: 2.0095. Min Act: -0.0000

Data Index: 1179776 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.9907. Min Act: -0.0000

Data Index: 681213 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.9979. Min Act: -0.0000

Data Index: 1073383 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.8309. Min Act: -0.0000

Data Index: 546919 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.8201. Min Act: -0.0000

Data Index: 314661 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.7486. Min Act: -0.0000

Data Index: 709891 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.7102. Min Act: -0.0000

Data Index: 737154 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.6727. Min Act: -0.0000

Data Index: 1208911 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.6676. Min Act: -0.0000

Data Index: 940785 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.6229. Min Act: -0.0000

Data Index: 184608 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.6318. Min Act: -0.0000

Data Index: 1299869 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.6314. Min Act: -0.0000

Data Index: 1145109 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.5321. Min Act: -0.0000

Data Index: 269732 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.5974. Min Act: -0.0000

Data Index: 809426 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.5977. Min Act: -0.0000

Data Index: 1327178 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.5979. Min Act: -0.0000

Data Index: 1142690 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.5731. Min Act: -0.0000

Data Index: 146101 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.5612. Min Act: -0.0000

Data Index: 683770 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 2.0095. Min Range: -2.0095

Max Act: 1.5637. Min Act: -0.0000

Data Index: 1242126 (C4 (Web Text))

Max Activating Token Index: 557