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

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

Neuron 3032 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: 2.7584. Min Range: -2.7584

Max Act: 2.7584. Min Act: -0.0000

Data Index: 154734 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 2.7584. Min Range: -2.7584

Max Act: 2.2451. Min Act: -0.0000

Data Index: 1504920 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 2.7584. Min Range: -2.7584

Max Act: 2.1448. Min Act: -0.0000

Data Index: 1623862 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 2.7584. Min Range: -2.7584

Max Act: 2.1052. Min Act: -0.0000

Data Index: 1611679 (Python Code)

Max Activating Token Index: 201

Text #4

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.9800. Min Act: -0.0000

Data Index: 1534137 (Python Code)

Max Activating Token Index: 730

Text #5

Max Range: 2.7584. Min Range: -2.7584

Max Act: 2.1066. Min Act: -0.0000

Data Index: 1528549 (Python Code)

Max Activating Token Index: 698

Text #6

Max Range: 2.7584. Min Range: -2.7584

Max Act: 2.0919. Min Act: -0.0000

Data Index: 1442484 (Python Code)

Max Activating Token Index: 892

Text #7

Max Range: 2.7584. Min Range: -2.7584

Max Act: 2.0983. Min Act: -0.0000

Data Index: 1564203 (Python Code)

Max Activating Token Index: 730

Text #8

Max Range: 2.7584. Min Range: -2.7584

Max Act: 2.1066. Min Act: -0.0000

Data Index: 1529784 (Python Code)

Max Activating Token Index: 119

Text #9

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.9926. Min Act: -0.0000

Data Index: 1597585 (Python Code)

Max Activating Token Index: 830

Text #10

Max Range: 2.7584. Min Range: -2.7584

Max Act: 2.0821. Min Act: -0.0000

Data Index: 1562149 (Python Code)

Max Activating Token Index: 764

Text #11

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.8499. Min Act: -0.0000

Data Index: 1503583 (Python Code)

Max Activating Token Index: 308

Text #12

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.6875. Min Act: -0.0000

Data Index: 95144 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.8974. Min Act: -0.0000

Data Index: 424634 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.8811. Min Act: -0.0000

Data Index: 1388736 (Python Code)

Max Activating Token Index: 982

Text #15

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1428696 (Python Code)

Max Activating Token Index: 255

Text #16

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.7738. Min Act: -0.0000

Data Index: 1601389 (Python Code)

Max Activating Token Index: 1017

Text #17

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.8683. Min Act: -0.0000

Data Index: 1516153 (Python Code)

Max Activating Token Index: 490

Text #18

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.9556. Min Act: -0.0000

Data Index: 1482573 (Python Code)

Max Activating Token Index: 701

Text #19

Max Range: 2.7584. Min Range: -2.7584

Max Act: 1.9426. Min Act: -0.0000

Data Index: 1546229 (Python Code)

Max Activating Token Index: 939