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

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

Neuron 5360 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6018. Min Range: -5.6018

Max Act: 5.6018. Min Act: -0.0000

Data Index: 594165 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.6786. Min Act: -0.0000

Data Index: 144001 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.9766. Min Act: -0.0000

Data Index: 1269386 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.8913. Min Act: -0.0000

Data Index: 602936 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.5544. Min Act: -0.0000

Data Index: 972677 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.5442. Min Act: -0.0000

Data Index: 1653629 (Python Code)

Max Activating Token Index: 886

Text #6

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.3727. Min Act: -0.0000

Data Index: 931454 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.2397. Min Act: -0.0000

Data Index: 854643 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.5240. Min Act: -0.0000

Data Index: 1494884 (Python Code)

Max Activating Token Index: 920

Text #9

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.3318. Min Act: -0.0000

Data Index: 759806 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.3404. Min Act: -0.0000

Data Index: 1355828 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.4475. Min Act: -0.0000

Data Index: 254293 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.0934. Min Act: -0.0000

Data Index: 1331366 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.1692. Min Act: -0.0000

Data Index: 957458 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.1320. Min Act: -0.0000

Data Index: 960593 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.0793. Min Act: -0.0000

Data Index: 1126850 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.0930. Min Act: -0.0000

Data Index: 116874 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.2348. Min Act: -0.0000

Data Index: 394929 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.0718. Min Act: -0.0000

Data Index: 1317276 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 5.6018. Min Range: -5.6018

Max Act: 3.1757. Min Act: -0.0000

Data Index: 737799 (C4 (Web Text))

Max Activating Token Index: 41