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

Dataset: The Pile

Neuron 1160 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5101. Min Range: -3.5101

Max Act: 3.5101. Min Act: -0.0000

Data Index: 871588 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 3.5101. Min Range: -3.5101

Max Act: 3.3712. Min Act: -0.0000

Data Index: 1326887 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 3.5101. Min Range: -3.5101

Max Act: 3.0678. Min Act: -0.0000

Data Index: 270311 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 3.5101. Min Range: -3.5101

Max Act: 3.0717. Min Act: -0.0000

Data Index: 515599 (The Pile)

Max Activating Token Index: 167

Text #4

Max Range: 3.5101. Min Range: -3.5101

Max Act: 3.0469. Min Act: -0.0000

Data Index: 688652 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.9726. Min Act: -0.0000

Data Index: 1690017 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.9464. Min Act: -0.0000

Data Index: 1965920 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.9394. Min Act: -0.0000

Data Index: 1219774 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 3.5101. Min Range: -3.5101

Max Act: 3.0164. Min Act: -0.0000

Data Index: 437722 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 3.5101. Min Range: -3.5101

Max Act: 3.0249. Min Act: -0.0000

Data Index: 1086835 (The Pile)

Max Activating Token Index: 56

Text #10

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.7517. Min Act: -0.0000

Data Index: 39041 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.8596. Min Act: -0.0000

Data Index: 279009 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 3.5101. Min Range: -3.5101

Max Act: 3.1076. Min Act: -0.0000

Data Index: 1416282 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.9156. Min Act: -0.0000

Data Index: 1353376 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.9062. Min Act: -0.0000

Data Index: 720747 (The Pile)

Max Activating Token Index: 855

Text #15

Max Range: 3.5101. Min Range: -3.5101

Max Act: 3.0226. Min Act: -0.0000

Data Index: 1733621 (The Pile)

Max Activating Token Index: 969

Text #16

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.8447. Min Act: -0.0000

Data Index: 1228079 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.6884. Min Act: -0.0000

Data Index: 1002916 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.6399. Min Act: -0.0000

Data Index: 1053332 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 3.5101. Min Range: -3.5101

Max Act: 2.7916. Min Act: -0.0000

Data Index: 169089 (The Pile)

Max Activating Token Index: 361