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

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

Neuron 3768 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3794. Min Range: -3.3794

Max Act: 3.3794. Min Act: -0.0000

Data Index: 829179 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.2703. Min Act: -0.0001

Data Index: 756132 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.9738. Min Act: -0.0000

Data Index: 439408 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.6738. Min Act: -0.0001

Data Index: 977623 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.5615. Min Act: -0.0000

Data Index: 54892 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.5157. Min Act: -0.0000

Data Index: 612181 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.4315. Min Act: -0.0001

Data Index: 1229364 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.5517. Min Act: -0.0001

Data Index: 153029 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.5053. Min Act: -0.0000

Data Index: 708943 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.4555. Min Act: -0.0001

Data Index: 456949 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.4579. Min Act: -0.0000

Data Index: 910443 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.4363. Min Act: -0.0000

Data Index: 722153 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.5671. Min Act: -0.0000

Data Index: 845660 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.4309. Min Act: -0.0001

Data Index: 832620 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.3857. Min Act: -0.0001

Data Index: 588778 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.6098. Min Act: -0.0000

Data Index: 1000214 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.4346. Min Act: -0.0001

Data Index: 54313 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.3209. Min Act: -0.0000

Data Index: 878500 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.1846. Min Act: -0.0001

Data Index: 631311 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 3.3794. Min Range: -3.3794

Max Act: 2.3267. Min Act: -0.0001

Data Index: 177287 (C4 (Web Text))

Max Activating Token Index: 327