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

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

Neuron 4750 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: 1.8770. Min Range: -1.8770

Max Act: 1.8100. Min Act: -0.0000

Data Index: 434350 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.8770. Min Act: -0.0000

Data Index: 472735 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.5971. Min Act: -0.0000

Data Index: 52504 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.6848. Min Act: -0.0000

Data Index: 375078 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.5023. Min Act: -0.0000

Data Index: 1279901 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.6488. Min Act: -0.0000

Data Index: 663918 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.5880. Min Act: -0.0000

Data Index: 188340 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.5649. Min Act: -0.0000

Data Index: 422739 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.5679. Min Act: -0.0000

Data Index: 579820 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.6251. Min Act: -0.0000

Data Index: 1169686 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.4924. Min Act: -0.0000

Data Index: 661431 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.4687. Min Act: -0.0000

Data Index: 725448 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.3064. Min Act: -0.0000

Data Index: 724307 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.3520. Min Act: -0.0000

Data Index: 576121 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.3477. Min Act: -0.0000

Data Index: 445502 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.4172. Min Act: -0.0000

Data Index: 421185 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.3366. Min Act: -0.0000

Data Index: 822517 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.4033. Min Act: -0.0000

Data Index: 432373 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.3975. Min Act: -0.0000

Data Index: 143130 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.3821. Min Act: -0.0000

Data Index: 240757 (C4 (Web Text))

Max Activating Token Index: 177