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

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

Neuron 1734 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: 0.9656. Min Range: -0.9656

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1612623 (Python Code)

Max Activating Token Index: 471

Text #1

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1399340 (Python Code)

Max Activating Token Index: 358

Text #2

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6140. Min Act: -0.0000

Data Index: 181980 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.6344. Min Act: -0.0000

Data Index: 297485 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1394270 (Python Code)

Max Activating Token Index: 1010

Text #5

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.4387. Min Act: 0.0000

Data Index: 1019854 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1253888 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.4712. Min Act: -0.0000

Data Index: 47548 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1480241 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.4155. Min Act: -0.0000

Data Index: 366293 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.4581. Min Act: -0.0000

Data Index: 408145 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.3963. Min Act: -0.0000

Data Index: 57696 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.3759. Min Act: 0.0000

Data Index: 1283997 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.3833. Min Act: -0.0000

Data Index: 246070 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.3462. Min Act: -0.0000

Data Index: 1474611 (Python Code)

Max Activating Token Index: 680

Text #15

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.3753. Min Act: -0.0000

Data Index: 249719 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1034946 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.3037. Min Act: -0.0000

Data Index: 276229 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.3554. Min Act: 0.0000

Data Index: 1261324 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.9656. Min Range: -0.9656

Max Act: 0.3296. Min Act: -0.0000

Data Index: 1292146 (C4 (Web Text))

Max Activating Token Index: 842