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

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

Neuron 806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9078. Min Range: -3.9078

Max Act: 3.9078. Min Act: -0.0000

Data Index: 670478 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 3.9078. Min Range: -3.9078

Max Act: 3.6845. Min Act: -0.0000

Data Index: 392871 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 3.9078. Min Range: -3.9078

Max Act: 3.1143. Min Act: -0.0000

Data Index: 330357 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.9746. Min Act: -0.0000

Data Index: 892344 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 3.9078. Min Range: -3.9078

Max Act: 3.0725. Min Act: -0.0000

Data Index: 1242505 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.7962. Min Act: -0.0000

Data Index: 1232609 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.7473. Min Act: -0.0000

Data Index: 1263350 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.8952. Min Act: -0.0000

Data Index: 862231 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.8627. Min Act: -0.0000

Data Index: 595624 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.6871. Min Act: -0.0000

Data Index: 178800 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.6941. Min Act: -0.0000

Data Index: 1334707 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.9333. Min Act: -0.0000

Data Index: 218203 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.7485. Min Act: -0.0000

Data Index: 140709 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.7989. Min Act: -0.0000

Data Index: 1217119 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.6524. Min Act: -0.0000

Data Index: 12916 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.6444. Min Act: -0.0000

Data Index: 292938 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.5976. Min Act: -0.0000

Data Index: 455196 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.4579. Min Act: -0.0000

Data Index: 512570 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.5871. Min Act: -0.0000

Data Index: 745842 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 3.9078. Min Range: -3.9078

Max Act: 2.5756. Min Act: -0.0000

Data Index: 1250650 (C4 (Web Text))

Max Activating Token Index: 883