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

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

Neuron 5800 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.5234. Min Act: -0.0000

Data Index: 394674 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4886. Min Act: -0.0000

Data Index: 220240 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4019. Min Act: -0.0000

Data Index: 742052 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4008. Min Act: -0.0000

Data Index: 316075 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1282384 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3698. Min Act: -0.0000

Data Index: 587141 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4039. Min Act: -0.0000

Data Index: 848469 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3824. Min Act: -0.0000

Data Index: 777913 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3745. Min Act: -0.0000

Data Index: 113177 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1180601 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1176085 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3518. Min Act: -0.0000

Data Index: 88208 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3713. Min Act: -0.0000

Data Index: 716602 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3472. Min Act: -0.0000

Data Index: 33742 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1519964 (Python Code)

Max Activating Token Index: 825

Text #15

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3371. Min Act: 0.0001

Data Index: 433993 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3239. Min Act: -0.0000

Data Index: 281643 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3602. Min Act: -0.0000

Data Index: 862558 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1117143 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3239. Min Act: -0.0000

Data Index: 771686 (C4 (Web Text))

Max Activating Token Index: 249