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

Dataset: The Pile

Neuron 2891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8480. Min Act: -0.0000

Data Index: 758854 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1217266 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8046. Min Act: -0.0000

Data Index: 498826 (The Pile)

Max Activating Token Index: 113

Text #3

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8571. Min Act: -0.0000

Data Index: 834343 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1009793 (The Pile)

Max Activating Token Index: 711

Text #5

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8996. Min Act: -0.0000

Data Index: 362352 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1111169 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7877. Min Act: -0.0000

Data Index: 551428 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.8205. Min Act: -0.0000

Data Index: 71578 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1901930 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7662. Min Act: -0.0000

Data Index: 630852 (The Pile)

Max Activating Token Index: 150

Text #11

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1105386 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7663. Min Act: -0.0000

Data Index: 407061 (The Pile)

Max Activating Token Index: 708

Text #13

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7118. Min Act: -0.0000

Data Index: 998712 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7762. Min Act: -0.0000

Data Index: 678639 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1404348 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7812. Min Act: -0.0000

Data Index: 801130 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1961321 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1421554 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.8996. Min Range: -0.8996

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1284543 (The Pile)

Max Activating Token Index: 131