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

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

Neuron 3581 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3792. Min Act: -0.0003

Data Index: 371652 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3586. Min Act: -0.0003

Data Index: 301620 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3413. Min Act: -0.0002

Data Index: 1267064 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3098. Min Act: -0.0002

Data Index: 1286853 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3306. Min Act: -0.0002

Data Index: 972374 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3151. Min Act: -0.0002

Data Index: 215170 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3108. Min Act: -0.0003

Data Index: 732009 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.3011. Min Act: -0.0002

Data Index: 660157 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2995. Min Act: -0.0003

Data Index: 458635 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2990. Min Act: -0.0003

Data Index: 1629544 (Python Code)

Max Activating Token Index: 718

Text #10

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2850. Min Act: -0.0003

Data Index: 681724 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2952. Min Act: -0.0002

Data Index: 46163 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2891. Min Act: -0.0003

Data Index: 1308855 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2904. Min Act: -0.0002

Data Index: 793217 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2998. Min Act: -0.0003

Data Index: 990280 (C4 (Web Text))

Max Activating Token Index: 954

Text #15

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2884. Min Act: -0.0002

Data Index: 573985 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2788. Min Act: -0.0003

Data Index: 905824 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2808. Min Act: -0.0002

Data Index: 459284 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2715. Min Act: -0.0002

Data Index: 772067 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.3792. Min Range: -0.3792

Max Act: 0.2752. Min Act: -0.0003

Data Index: 1579284 (Python Code)

Max Activating Token Index: 745