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

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

Neuron 4064 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0870. Min Act: -0.0000

Data Index: 41550 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0871. Min Act: -0.0000

Data Index: 938127 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0889. Min Act: -0.0000

Data Index: 160640 (C4 (Web Text))

Max Activating Token Index: 611

Text #3

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0796. Min Act: -0.0000

Data Index: 352422 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0856. Min Act: -0.0000

Data Index: 525766 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0807. Min Act: -0.0000

Data Index: 49696 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0778. Min Act: -0.0000

Data Index: 288661 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0793. Min Act: -0.0000

Data Index: 37290 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0763. Min Act: -0.0000

Data Index: 941527 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0761. Min Act: -0.0000

Data Index: 64028 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0775. Min Act: -0.0000

Data Index: 426837 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0754. Min Act: -0.0000

Data Index: 325994 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0750. Min Act: -0.0000

Data Index: 1357948 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0774. Min Act: -0.0000

Data Index: 837066 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0765. Min Act: -0.0000

Data Index: 452923 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0718. Min Act: -0.0000

Data Index: 487685 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0701. Min Act: -0.0000

Data Index: 59840 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1108564 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0739. Min Act: -0.0000

Data Index: 210728 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.0889. Min Range: -0.0889

Max Act: 0.0726. Min Act: -0.0000

Data Index: 664655 (C4 (Web Text))

Max Activating Token Index: 65