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

Dataset: The Pile

Neuron 4545 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: 0.8662. Min Range: -0.8662

Max Act: 0.8662. Min Act: -0.0000

Data Index: 193029 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.7661. Min Act: -0.0000

Data Index: 682893 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5873. Min Act: -0.0000

Data Index: 884199 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1474302 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1401698 (The Pile)

Max Activating Token Index: 927

Text #5

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5652. Min Act: -0.0000

Data Index: 945670 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1573939 (The Pile)

Max Activating Token Index: 763

Text #7

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5018. Min Act: -0.0000

Data Index: 723299 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1453932 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1233604 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1038815 (The Pile)

Max Activating Token Index: 292

Text #11

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5327. Min Act: -0.0000

Data Index: 803911 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1742235 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5204. Min Act: -0.0000

Data Index: 814581 (The Pile)

Max Activating Token Index: 873

Text #14

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1021813 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1725972 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4467. Min Act: -0.0000

Data Index: 427340 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1344002 (The Pile)

Max Activating Token Index: 996

Text #18

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.5240. Min Act: -0.0000

Data Index: 80223 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.8662. Min Range: -0.8662

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1614901 (The Pile)

Max Activating Token Index: 596