Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4902 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.3890. Min Act: -0.0000

Data Index: 906740 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1531883 (Python Code)

Max Activating Token Index: 407

Text #2

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.1867. Min Act: -0.0000

Data Index: 1627309 (Python Code)

Max Activating Token Index: 264

Text #3

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.2374. Min Act: -0.0000

Data Index: 1392847 (Python Code)

Max Activating Token Index: 677

Text #4

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.2874. Min Act: -0.0000

Data Index: 94699 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1429807 (Python Code)

Max Activating Token Index: 794

Text #6

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.2861. Min Act: -0.0000

Data Index: 1533174 (Python Code)

Max Activating Token Index: 61

Text #7

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1559227 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.1289. Min Act: -0.0000

Data Index: 883590 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.1459. Min Act: -0.0000

Data Index: 692589 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1656291 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.2094. Min Act: -0.0000

Data Index: 722227 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.1756. Min Act: -0.0000

Data Index: 1571103 (Python Code)

Max Activating Token Index: 455

Text #13

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1640861 (Python Code)

Max Activating Token Index: 776

Text #14

Max Range: 1.3890. Min Range: -1.3890

Max Act: 0.9608. Min Act: -0.0000

Data Index: 989778 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.0955. Min Act: -0.0000

Data Index: 1427177 (Python Code)

Max Activating Token Index: 544

Text #16

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.0569. Min Act: -0.0000

Data Index: 1399519 (Python Code)

Max Activating Token Index: 653

Text #17

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1483455 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.0801. Min Act: -0.0000

Data Index: 1654071 (Python Code)

Max Activating Token Index: 976

Text #19

Max Range: 1.3890. Min Range: -1.3890

Max Act: 1.0246. Min Act: -0.0000

Data Index: 697431 (C4 (Web Text))

Max Activating Token Index: 434