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

Dataset: The Pile

Neuron 1640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.8897. Min Act: -0.0000

Data Index: 1158916 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.9576. Min Act: -0.0000

Data Index: 1726548 (The Pile)

Max Activating Token Index: 991

Text #2

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.5780. Min Act: -0.0000

Data Index: 231264 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.7190. Min Act: -0.0000

Data Index: 701720 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.5032. Min Act: -0.0000

Data Index: 1213920 (The Pile)

Max Activating Token Index: 511

Text #5

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.6754. Min Act: -0.0000

Data Index: 529700 (The Pile)

Max Activating Token Index: 30

Text #6

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.5493. Min Act: -0.0000

Data Index: 1506576 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1841788 (The Pile)

Max Activating Token Index: 451

Text #8

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.4540. Min Act: -0.0000

Data Index: 1659691 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.4507. Min Act: -0.0000

Data Index: 1381219 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1650575 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3094. Min Act: -0.0000

Data Index: 1346997 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3526. Min Act: -0.0000

Data Index: 961909 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1678996 (The Pile)

Max Activating Token Index: 585

Text #14

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1509158 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.5287. Min Act: -0.0000

Data Index: 834386 (The Pile)

Max Activating Token Index: 768

Text #16

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.3539. Min Act: -0.0000

Data Index: 959007 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2324. Min Act: -0.0000

Data Index: 26456 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2892. Min Act: -0.0000

Data Index: 785441 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 1.9576. Min Range: -1.9576

Max Act: 1.2918. Min Act: -0.0000

Data Index: 472641 (The Pile)

Max Activating Token Index: 936