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

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

Neuron 2745 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.5704. Min Act: -0.0000

Data Index: 78150 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.4497. Min Act: -0.0000

Data Index: 963095 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.2798. Min Act: -0.0000

Data Index: 957765 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.3840. Min Act: -0.0000

Data Index: 665951 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.2598. Min Act: -0.0000

Data Index: 574850 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.2445. Min Act: -0.0000

Data Index: 523082 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.0940. Min Act: -0.0000

Data Index: 599826 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.0843. Min Act: -0.0000

Data Index: 262592 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.0564. Min Act: -0.0000

Data Index: 40432 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.1588. Min Act: -0.0000

Data Index: 28298 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.2668. Min Act: -0.0000

Data Index: 524256 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 2.5704. Min Range: -2.5704

Max Act: 1.9786. Min Act: -0.0000

Data Index: 528344 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.1670. Min Act: -0.0000

Data Index: 427709 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 2.5704. Min Range: -2.5704

Max Act: 1.9209. Min Act: -0.0000

Data Index: 777830 (C4 (Web Text))

Max Activating Token Index: 625

Text #14

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.1517. Min Act: -0.0000

Data Index: 985449 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 2.5704. Min Range: -2.5704

Max Act: 2.0151. Min Act: -0.0000

Data Index: 264920 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 2.5704. Min Range: -2.5704

Max Act: 1.8914. Min Act: -0.0000

Data Index: 106485 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 2.5704. Min Range: -2.5704

Max Act: 1.8967. Min Act: 0.0004

Data Index: 1218189 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 2.5704. Min Range: -2.5704

Max Act: 1.9745. Min Act: -0.0000

Data Index: 128151 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 2.5704. Min Range: -2.5704

Max Act: 1.8747. Min Act: -0.0000

Data Index: 1215188 (C4 (Web Text))

Max Activating Token Index: 323