Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2782 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1807. Min Range: -1.1807

Max Act: 1.1807. Min Act: -0.0001

Data Index: 330346 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.9360. Min Act: -0.0001

Data Index: 53705 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8320. Min Act: -0.0001

Data Index: 482485 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7538. Min Act: -0.0001

Data Index: 304891 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8632. Min Act: -0.0001

Data Index: 347810 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7898. Min Act: -0.0001

Data Index: 397699 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7836. Min Act: -0.0001

Data Index: 845008 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8058. Min Act: -0.0001

Data Index: 862131 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8434. Min Act: -0.0001

Data Index: 592458 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7591. Min Act: -0.0001

Data Index: 885198 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.8054. Min Act: -0.0001

Data Index: 1276187 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.6885. Min Act: -0.0001

Data Index: 1150470 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7279. Min Act: -0.0001

Data Index: 788427 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7081. Min Act: -0.0001

Data Index: 328102 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.6804. Min Act: -0.0001

Data Index: 1351785 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7339. Min Act: -0.0001

Data Index: 487027 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1138763 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.6465. Min Act: -0.0001

Data Index: 65435 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.7017. Min Act: -0.0001

Data Index: 1063058 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.1807. Min Range: -1.1807

Max Act: 0.6416. Min Act: -0.0001

Data Index: 998496 (C4 (Web Text))

Max Activating Token Index: 544