Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2801 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.8971. Min Act: -0.0000

Data Index: 922481 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.8943. Min Act: -0.0001

Data Index: 1482652 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.6410. Min Act: -0.0001

Data Index: 1230564 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.4990. Min Act: -0.0000

Data Index: 888533 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.5803. Min Act: -0.0000

Data Index: 1460876 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.3204. Min Act: -0.0000

Data Index: 1553411 (Python Code)

Max Activating Token Index: 598

Text #6

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1381049 (Python Code)

Max Activating Token Index: 87

Text #7

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.2056. Min Act: -0.0001

Data Index: 1564360 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.2562. Min Act: -0.0001

Data Index: 1360927 (Python Code)

Max Activating Token Index: 850

Text #9

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1040506 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.1959. Min Act: -0.0000

Data Index: 1144019 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.1628. Min Act: -0.0001

Data Index: 1504462 (Python Code)

Max Activating Token Index: 210

Text #12

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.2737. Min Act: -0.0000

Data Index: 1586367 (Python Code)

Max Activating Token Index: 750

Text #13

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1492387 (Python Code)

Max Activating Token Index: 93

Text #14

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.1383. Min Act: -0.0000

Data Index: 802564 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.1647. Min Act: -0.0001

Data Index: 1412245 (Python Code)

Max Activating Token Index: 746

Text #16

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1535436 (Python Code)

Max Activating Token Index: 197

Text #17

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.0900. Min Act: -0.0001

Data Index: 1405447 (Python Code)

Max Activating Token Index: 487

Text #18

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.0951. Min Act: -0.0001

Data Index: 138255 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.8971. Min Range: -1.8971

Max Act: 1.1902. Min Act: -0.0001

Data Index: 1388906 (Python Code)

Max Activating Token Index: 833