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

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

Neuron 4902 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: 0.7303. Min Range: -0.7303

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1150246 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7153. Min Act: -0.0000

Data Index: 282640 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6639. Min Act: -0.0000

Data Index: 857165 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6621. Min Act: -0.0000

Data Index: 906459 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1464696 (Python Code)

Max Activating Token Index: 566

Text #5

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1174711 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7045. Min Act: -0.0000

Data Index: 39285 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6632. Min Act: -0.0000

Data Index: 528603 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6455. Min Act: -0.0000

Data Index: 624261 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6377. Min Act: 0.0000

Data Index: 691322 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6370. Min Act: -0.0000

Data Index: 575429 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5922. Min Act: -0.0000

Data Index: 397650 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6184. Min Act: -0.0000

Data Index: 1112616 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6044. Min Act: 0.0000

Data Index: 141738 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5755. Min Act: -0.0000

Data Index: 851520 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1418113 (Python Code)

Max Activating Token Index: 638

Text #16

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6276. Min Act: -0.0000

Data Index: 350673 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5882. Min Act: -0.0000

Data Index: 1279747 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5741. Min Act: -0.0000

Data Index: 834197 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1080986 (C4 (Web Text))

Max Activating Token Index: 849