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

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

Neuron 3856 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.5797. Min Act: -0.0001

Data Index: 433292 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.4637. Min Act: -0.0001

Data Index: 1170366 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.5099. Min Act: -0.0001

Data Index: 1193980 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.4021. Min Act: -0.0001

Data Index: 771 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.3106. Min Act: -0.0001

Data Index: 894853 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.0810. Min Act: -0.0001

Data Index: 847647 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.5044. Min Act: -0.0001

Data Index: 1095373 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.3046. Min Act: -0.0001

Data Index: 751884 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.4401. Min Act: -0.0001

Data Index: 882646 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.3252. Min Act: -0.0001

Data Index: 964483 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.3110. Min Act: -0.0001

Data Index: 64276 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.2588. Min Act: -0.0001

Data Index: 1196159 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1752. Min Act: -0.0001

Data Index: 677944 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.3099. Min Act: -0.0001

Data Index: 161048 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.3339. Min Act: -0.0001

Data Index: 29691 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1945. Min Act: -0.0001

Data Index: 386474 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1017. Min Act: -0.0001

Data Index: 921371 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.2551. Min Act: -0.0001

Data Index: 313601 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1587. Min Act: -0.0001

Data Index: 61886 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 1.5797. Min Range: -1.5797

Max Act: 1.1196. Min Act: -0.0001

Data Index: 265140 (C4 (Web Text))

Max Activating Token Index: 1016