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

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

Neuron 311 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: 0.5355. Min Range: -0.5355

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1060365 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1034669 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.3280. Min Act: -0.0000

Data Index: 884098 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.2786. Min Act: -0.0000

Data Index: 969228 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.2789. Min Act: -0.0000

Data Index: 1195672 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.2844. Min Act: -0.0000

Data Index: 335666 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.2610. Min Act: -0.0000

Data Index: 34646 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.2172. Min Act: -0.0000

Data Index: 224807 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.2166. Min Act: -0.0000

Data Index: 867043 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1127653 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.2033. Min Act: -0.0000

Data Index: 776345 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.2164. Min Act: -0.0000

Data Index: 120915 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1268029 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.1873. Min Act: -0.0000

Data Index: 83218 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.1733. Min Act: -0.0000

Data Index: 413367 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.1472. Min Act: -0.0000

Data Index: 339664 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.1381. Min Act: -0.0000

Data Index: 46120 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.1415. Min Act: -0.0000

Data Index: 878238 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1012836 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.5355. Min Range: -0.5355

Max Act: 0.0841. Min Act: -0.0000

Data Index: 839500 (C4 (Web Text))

Max Activating Token Index: 409