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

Dataset: The Pile

Neuron 4558 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1718. Min Range: -1.1718

Max Act: 1.1718. Min Act: -0.0000

Data Index: 1937212 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7968. Min Act: -0.0000

Data Index: 888960 (The Pile)

Max Activating Token Index: 608

Text #2

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.7711. Min Act: -0.0000

Data Index: 1140014 (The Pile)

Max Activating Token Index: 106

Text #3

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6687. Min Act: -0.0000

Data Index: 834277 (The Pile)

Max Activating Token Index: 67

Text #4

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6593. Min Act: -0.0000

Data Index: 965838 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1473476 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1527955 (The Pile)

Max Activating Token Index: 543

Text #7

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6212. Min Act: -0.0000

Data Index: 840433 (The Pile)

Max Activating Token Index: 897

Text #8

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1395836 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6525. Min Act: -0.0000

Data Index: 322886 (The Pile)

Max Activating Token Index: 104

Text #10

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.5622. Min Act: -0.0000

Data Index: 33937 (The Pile)

Max Activating Token Index: 841

Text #11

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1754609 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6478. Min Act: -0.0000

Data Index: 806482 (The Pile)

Max Activating Token Index: 367

Text #13

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1964660 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1178555 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1460694 (The Pile)

Max Activating Token Index: 842

Text #16

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1343531 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.5765. Min Act: -0.0000

Data Index: 253501 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.6214. Min Act: -0.0000

Data Index: 211924 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 1.1718. Min Range: -1.1718

Max Act: 0.4907. Min Act: -0.0000

Data Index: 433754 (The Pile)

Max Activating Token Index: 62