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

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

Neuron 4061 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.1999. Min Act: -0.0000

Data Index: 558313 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.1662. Min Act: -0.0000

Data Index: 140633 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.1299. Min Act: -0.0000

Data Index: 642815 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.2111. Min Act: -0.0000

Data Index: 1209828 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.0427. Min Act: -0.0000

Data Index: 502221 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.2807. Min Act: -0.0000

Data Index: 297593 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.0604. Min Act: -0.0000

Data Index: 1002022 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 2.2807. Min Range: -2.2807

Max Act: 1.9647. Min Act: -0.0000

Data Index: 413132 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.2769. Min Act: -0.0000

Data Index: 960138 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.0627. Min Act: -0.0000

Data Index: 908612 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 2.2807. Min Range: -2.2807

Max Act: 1.9444. Min Act: -0.0000

Data Index: 398959 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.0428. Min Act: -0.0000

Data Index: 444627 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.1467. Min Act: -0.0000

Data Index: 842304 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 2.2807. Min Range: -2.2807

Max Act: 1.8044. Min Act: -0.0000

Data Index: 1056660 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.0078. Min Act: -0.0000

Data Index: 105496 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 2.2807. Min Range: -2.2807

Max Act: 2.0089. Min Act: -0.0000

Data Index: 36167 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 2.2807. Min Range: -2.2807

Max Act: 1.8948. Min Act: -0.0000

Data Index: 1090629 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 2.2807. Min Range: -2.2807

Max Act: 1.9873. Min Act: -0.0000

Data Index: 1159816 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 2.2807. Min Range: -2.2807

Max Act: 1.8689. Min Act: -0.0000

Data Index: 255810 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 2.2807. Min Range: -2.2807

Max Act: 1.9779. Min Act: -0.0000

Data Index: 1079904 (C4 (Web Text))

Max Activating Token Index: 66