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

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

Neuron 1226 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: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0000

Data Index: 785734 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0674. Min Act: -0.0000

Data Index: 1191995 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0629. Min Act: -0.0000

Data Index: 928206 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0601. Min Act: -0.0000

Data Index: 610537 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0640. Min Act: -0.0000

Data Index: 688853 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0600. Min Act: -0.0000

Data Index: 343817 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0598. Min Act: -0.0000

Data Index: 370420 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1252762 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0589. Min Act: -0.0000

Data Index: 636776 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0518. Min Act: -0.0000

Data Index: 617535 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1025347 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0509. Min Act: -0.0000

Data Index: 680298 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0477. Min Act: -0.0000

Data Index: 360131 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0482. Min Act: -0.0000

Data Index: 354491 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0493. Min Act: -0.0000

Data Index: 338997 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0507. Min Act: -0.0000

Data Index: 247637 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0484. Min Act: -0.0000

Data Index: 662183 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0456. Min Act: -0.0000

Data Index: 231829 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0486. Min Act: -0.0000

Data Index: 333973 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0474. Min Act: -0.0000

Data Index: 857565 (C4 (Web Text))

Max Activating Token Index: 218