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

Dataset: The Pile

Neuron 1383 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: 0.4608. Min Range: -0.4608

Max Act: 0.4231. Min Act: -0.0000

Data Index: 974263 (The Pile)

Max Activating Token Index: 708

Text #1

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1280466 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1485035 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.4118. Min Act: -0.0000

Data Index: 224833 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1600778 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.4014. Min Act: -0.0000

Data Index: 488377 (The Pile)

Max Activating Token Index: 679

Text #6

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1930661 (The Pile)

Max Activating Token Index: 506

Text #7

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3916. Min Act: -0.0000

Data Index: 1053685 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1379205 (The Pile)

Max Activating Token Index: 12

Text #9

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3876. Min Act: -0.0000

Data Index: 94576 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3933. Min Act: -0.0000

Data Index: 1607234 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3674. Min Act: -0.0000

Data Index: 9717 (The Pile)

Max Activating Token Index: 135

Text #12

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1741170 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3652. Min Act: -0.0000

Data Index: 1057687 (The Pile)

Max Activating Token Index: 495

Text #14

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3846. Min Act: -0.0000

Data Index: 270550 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1846951 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3724. Min Act: -0.0000

Data Index: 166836 (The Pile)

Max Activating Token Index: 977

Text #17

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3704. Min Act: -0.0000

Data Index: 502846 (The Pile)

Max Activating Token Index: 102

Text #18

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3589. Min Act: -0.0000

Data Index: 660850 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 0.4608. Min Range: -0.4608

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1944512 (The Pile)

Max Activating Token Index: 578