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

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

Neuron 1822 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.8451. Min Act: -0.0001

Data Index: 9012 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7704. Min Act: -0.0001

Data Index: 1215785 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7431. Min Act: -0.0001

Data Index: 1224529 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7681. Min Act: -0.0001

Data Index: 893649 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7677. Min Act: -0.0001

Data Index: 1309555 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7569. Min Act: -0.0001

Data Index: 780912 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.5928. Min Act: -0.0001

Data Index: 1282801 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1236500 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1138116 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.6795. Min Act: -0.0001

Data Index: 577453 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.6722. Min Act: -0.0001

Data Index: 1145419 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.6927. Min Act: -0.0001

Data Index: 1076522 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.6069. Min Act: -0.0001

Data Index: 884653 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.6782. Min Act: -0.0001

Data Index: 855194 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.6739. Min Act: -0.0001

Data Index: 347656 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.5445. Min Act: -0.0001

Data Index: 315187 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.6352. Min Act: -0.0001

Data Index: 301727 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.6146. Min Act: -0.0001

Data Index: 117699 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.5854. Min Act: -0.0001

Data Index: 547947 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.8451. Min Range: -0.8451

Max Act: 0.5868. Min Act: -0.0001

Data Index: 935990 (C4 (Web Text))

Max Activating Token Index: 408