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

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

Neuron 4186 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: 2.5779. Min Range: -2.5779

Max Act: 2.5779. Min Act: -0.0000

Data Index: 860732 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 2.5779. Min Range: -2.5779

Max Act: 2.2688. Min Act: -0.0000

Data Index: 288799 (C4 (Web Text))

Max Activating Token Index: 214

Text #2

Max Range: 2.5779. Min Range: -2.5779

Max Act: 2.0647. Min Act: -0.0000

Data Index: 41016 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 2.5779. Min Range: -2.5779

Max Act: 2.1397. Min Act: -0.0000

Data Index: 1027498 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 2.5779. Min Range: -2.5779

Max Act: 2.0810. Min Act: -0.0000

Data Index: 784445 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.9133. Min Act: -0.0000

Data Index: 619383 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.7747. Min Act: -0.0000

Data Index: 641018 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.7210. Min Act: -0.0000

Data Index: 1047065 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.7807. Min Act: -0.0000

Data Index: 521747 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.6766. Min Act: -0.0000

Data Index: 763696 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.6558. Min Act: -0.0000

Data Index: 1114830 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.7513. Min Act: -0.0000

Data Index: 1050983 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.6416. Min Act: -0.0000

Data Index: 543775 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.8021. Min Act: -0.0000

Data Index: 207486 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.7019. Min Act: -0.0000

Data Index: 1022703 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.6990. Min Act: -0.0000

Data Index: 670730 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.6821. Min Act: -0.0000

Data Index: 658557 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.5846. Min Act: -0.0000

Data Index: 1139148 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.5570. Min Act: -0.0000

Data Index: 199882 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 2.5779. Min Range: -2.5779

Max Act: 1.6439. Min Act: -0.0000

Data Index: 401477 (C4 (Web Text))

Max Activating Token Index: 401