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

Dataset: The Pile

Neuron 1086 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: 0.8015. Min Range: -0.8015

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1504258 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1163401 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.7547. Min Act: -0.0000

Data Index: 525867 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6023. Min Act: -0.0000

Data Index: 259949 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6877. Min Act: -0.0000

Data Index: 431235 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.7829. Min Act: -0.0000

Data Index: 1745701 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6989. Min Act: -0.0000

Data Index: 784384 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6439. Min Act: -0.0000

Data Index: 621042 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6631. Min Act: -0.0000

Data Index: 143786 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1998741 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6416. Min Act: -0.0000

Data Index: 1327504 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1650869 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1545399 (The Pile)

Max Activating Token Index: 72

Text #13

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6307. Min Act: -0.0000

Data Index: 470673 (The Pile)

Max Activating Token Index: 961

Text #14

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6485. Min Act: -0.0000

Data Index: 1113806 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1214114 (The Pile)

Max Activating Token Index: 117

Text #16

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1288333 (The Pile)

Max Activating Token Index: 494

Text #17

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6637. Min Act: -0.0000

Data Index: 357460 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.7167. Min Act: -0.0000

Data Index: 674073 (The Pile)

Max Activating Token Index: 577

Text #19

Max Range: 0.8015. Min Range: -0.8015

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1719067 (The Pile)

Max Activating Token Index: 360