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

Dataset: The Pile

Neuron 4829 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: 0.6955. Min Range: -0.6955

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1937095 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6955. Min Act: -0.0000

Data Index: 1334883 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6017. Min Act: -0.0000

Data Index: 131863 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6440. Min Act: -0.0000

Data Index: 226475 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6139. Min Act: -0.0000

Data Index: 893842 (The Pile)

Max Activating Token Index: 61

Text #5

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6262. Min Act: -0.0000

Data Index: 400659 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5898. Min Act: -0.0000

Data Index: 417140 (The Pile)

Max Activating Token Index: 239

Text #7

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5824. Min Act: -0.0000

Data Index: 742439 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1614574 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1168846 (The Pile)

Max Activating Token Index: 587

Text #10

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1534063 (The Pile)

Max Activating Token Index: 991

Text #11

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5364. Min Act: -0.0000

Data Index: 751499 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5658. Min Act: -0.0000

Data Index: 301174 (The Pile)

Max Activating Token Index: 890

Text #13

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1795033 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5422. Min Act: -0.0000

Data Index: 486178 (The Pile)

Max Activating Token Index: 81

Text #15

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1068389 (The Pile)

Max Activating Token Index: 570

Text #16

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5128. Min Act: -0.0000

Data Index: 36939 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1316394 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4915. Min Act: -0.0000

Data Index: 870075 (The Pile)

Max Activating Token Index: 381

Text #19

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4757. Min Act: -0.0000

Data Index: 668503 (The Pile)

Max Activating Token Index: 831