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

Dataset: The Pile

Neuron 4499 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: 0.7101. Min Range: -0.7101

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1791449 (The Pile)

Max Activating Token Index: 69

Text #1

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1953883 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1192098 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1586385 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1437887 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1785894 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6261. Min Act: -0.0000

Data Index: 1863301 (The Pile)

Max Activating Token Index: 106

Text #7

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6245. Min Act: -0.0000

Data Index: 295504 (The Pile)

Max Activating Token Index: 908

Text #8

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5672. Min Act: -0.0000

Data Index: 138007 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5751. Min Act: -0.0000

Data Index: 175148 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5451. Min Act: -0.0000

Data Index: 1337331 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1171662 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1794935 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1158293 (The Pile)

Max Activating Token Index: 130

Text #14

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5118. Min Act: -0.0000

Data Index: 1139713 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1357638 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5394. Min Act: -0.0000

Data Index: 350920 (The Pile)

Max Activating Token Index: 707

Text #17

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5598. Min Act: -0.0000

Data Index: 55947 (The Pile)

Max Activating Token Index: 34

Text #18

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1270632 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 0.7101. Min Range: -0.7101

Max Act: 0.4620. Min Act: -0.0000

Data Index: 39368 (The Pile)

Max Activating Token Index: 753