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

Dataset: The Pile

Neuron 702 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3689. Min Range: -1.3689

Max Act: 1.3689. Min Act: -0.0000

Data Index: 680479 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 1.3689. Min Range: -1.3689

Max Act: 1.1202. Min Act: -0.0000

Data Index: 320151 (The Pile)

Max Activating Token Index: 101

Text #2

Max Range: 1.3689. Min Range: -1.3689

Max Act: 1.2084. Min Act: -0.0000

Data Index: 340528 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 1.3689. Min Range: -1.3689

Max Act: 1.0037. Min Act: -0.0000

Data Index: 124733 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.9640. Min Act: -0.0000

Data Index: 1583251 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 1.3689. Min Range: -1.3689

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1806829 (The Pile)

Max Activating Token Index: 723

Text #6

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1961314 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.9904. Min Act: -0.0000

Data Index: 55590 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.9175. Min Act: -0.0000

Data Index: 416380 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 1.3689. Min Range: -1.3689

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1882090 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1128557 (The Pile)

Max Activating Token Index: 452

Text #11

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8748. Min Act: -0.0000

Data Index: 855352 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1417615 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8797. Min Act: -0.0000

Data Index: 994075 (The Pile)

Max Activating Token Index: 771

Text #14

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1461698 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8615. Min Act: -0.0000

Data Index: 475569 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1683719 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1185103 (The Pile)

Max Activating Token Index: 79

Text #18

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1265973 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 1.3689. Min Range: -1.3689

Max Act: 0.8661. Min Act: -0.0000

Data Index: 868699 (The Pile)

Max Activating Token Index: 742