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

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

Neuron 3988 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4637. Min Range: -1.4637

Max Act: 1.3722. Min Act: -0.0000

Data Index: 916799 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.4637. Min Range: -1.4637

Max Act: 1.4637. Min Act: -0.0001

Data Index: 1537465 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 1.4637. Min Range: -1.4637

Max Act: 1.2398. Min Act: -0.0001

Data Index: 1556387 (Python Code)

Max Activating Token Index: 141

Text #3

Max Range: 1.4637. Min Range: -1.4637

Max Act: 1.1436. Min Act: -0.0001

Data Index: 1652697 (Python Code)

Max Activating Token Index: 73

Text #4

Max Range: 1.4637. Min Range: -1.4637

Max Act: 1.0406. Min Act: -0.0000

Data Index: 223936 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 1.4637. Min Range: -1.4637

Max Act: 1.0708. Min Act: -0.0000

Data Index: 1496931 (Python Code)

Max Activating Token Index: 44

Text #6

Max Range: 1.4637. Min Range: -1.4637

Max Act: 1.1024. Min Act: -0.0000

Data Index: 77453 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9156. Min Act: -0.0000

Data Index: 82518 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.8884. Min Act: -0.0000

Data Index: 1589673 (Python Code)

Max Activating Token Index: 716

Text #9

Max Range: 1.4637. Min Range: -1.4637

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1387765 (Python Code)

Max Activating Token Index: 63

Text #10

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1644511 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1350688 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 1.4637. Min Range: -1.4637

Max Act: 1.0014. Min Act: -0.0000

Data Index: 325961 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9518. Min Act: -0.0000

Data Index: 563150 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1006749 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9373. Min Act: -0.0000

Data Index: 1517535 (Python Code)

Max Activating Token Index: 105

Text #16

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1443973 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9878. Min Act: -0.0000

Data Index: 322034 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9884. Min Act: -0.0000

Data Index: 1424102 (Python Code)

Max Activating Token Index: 83

Text #19

Max Range: 1.4637. Min Range: -1.4637

Max Act: 0.9741. Min Act: -0.0000

Data Index: 251040 (C4 (Web Text))

Max Activating Token Index: 969