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

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

Neuron 539 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: 1.1368. Min Range: -1.1368

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1211877 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.0471. Min Act: -0.0000

Data Index: 662355 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.0454. Min Act: -0.0000

Data Index: 354855 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.0544. Min Act: -0.0000

Data Index: 52 (C4 (Web Text))

Max Activating Token Index: 178

Text #4

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9282. Min Act: -0.0000

Data Index: 183970 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9100. Min Act: -0.0000

Data Index: 760093 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9353. Min Act: -0.0000

Data Index: 676779 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.0072. Min Act: -0.0000

Data Index: 882727 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9953. Min Act: -0.0000

Data Index: 710246 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1016237 (C4 (Web Text))

Max Activating Token Index: 167

Text #10

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9350. Min Act: -0.0000

Data Index: 1095298 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9060. Min Act: -0.0000

Data Index: 752089 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9167. Min Act: -0.0000

Data Index: 604244 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8856. Min Act: -0.0001

Data Index: 712915 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1141874 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8842. Min Act: -0.0000

Data Index: 814630 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8853. Min Act: -0.0000

Data Index: 742646 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1251964 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8639. Min Act: -0.0001

Data Index: 363500 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8909. Min Act: -0.0000

Data Index: 965943 (C4 (Web Text))

Max Activating Token Index: 376