Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1595 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4624. Min Act: -0.0003

Data Index: 883454 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4306. Min Act: -0.0003

Data Index: 240715 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4137. Min Act: -0.0003

Data Index: 755456 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4355. Min Act: -0.0003

Data Index: 706264 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4325. Min Act: -0.0003

Data Index: 751381 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3886. Min Act: -0.0003

Data Index: 502801 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3868. Min Act: -0.0003

Data Index: 66341 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3826. Min Act: -0.0003

Data Index: 1134815 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4063. Min Act: -0.0003

Data Index: 53222 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4041. Min Act: -0.0003

Data Index: 679071 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3526. Min Act: -0.0003

Data Index: 726506 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.4149. Min Act: -0.0003

Data Index: 112204 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3999. Min Act: -0.0003

Data Index: 1002461 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3721. Min Act: -0.0003

Data Index: 77729 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3725. Min Act: -0.0003

Data Index: 366911 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3751. Min Act: -0.0003

Data Index: 480393 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3830. Min Act: -0.0003

Data Index: 239137 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3814. Min Act: -0.0003

Data Index: 561890 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3600. Min Act: -0.0003

Data Index: 168119 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 0.4624. Min Range: -0.4624

Max Act: 0.3946. Min Act: -0.0003

Data Index: 980812 (C4 (Web Text))

Max Activating Token Index: 26