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

Dataset: The Pile

Neuron 3968 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.8609. Min Act: -0.0000

Data Index: 848670 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.6658. Min Act: -0.0000

Data Index: 1496720 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.6891. Min Act: -0.0000

Data Index: 840481 (The Pile)

Max Activating Token Index: 719

Text #3

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.7031. Min Act: -0.0000

Data Index: 1816811 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5944. Min Act: -0.0000

Data Index: 417928 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.7753. Min Act: -0.0000

Data Index: 10277 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.7437. Min Act: -0.0000

Data Index: 839036 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.4440. Min Act: -0.0000

Data Index: 1870285 (The Pile)

Max Activating Token Index: 274

Text #8

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5941. Min Act: -0.0000

Data Index: 47442 (The Pile)

Max Activating Token Index: 150

Text #9

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5925. Min Act: -0.0000

Data Index: 19263 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1441390 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.6473. Min Act: -0.0000

Data Index: 217860 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5359. Min Act: -0.0000

Data Index: 1604772 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.4422. Min Act: -0.0000

Data Index: 1867551 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5467. Min Act: -0.0000

Data Index: 821416 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.4952. Min Act: -0.0000

Data Index: 161371 (The Pile)

Max Activating Token Index: 72

Text #16

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5127. Min Act: -0.0000

Data Index: 793331 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.5636. Min Act: -0.0000

Data Index: 558183 (The Pile)

Max Activating Token Index: 857

Text #18

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.4810. Min Act: -0.0000

Data Index: 1262039 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 1.8609. Min Range: -1.8609

Max Act: 1.3795. Min Act: -0.0000

Data Index: 1664317 (The Pile)

Max Activating Token Index: 167