Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2155 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7121. Min Range: -1.7121

Max Act: 1.7121. Min Act: -0.0000

Data Index: 148701 (The Pile)

Max Activating Token Index: 816

Text #1

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.8266. Min Act: -0.0000

Data Index: 127490 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1778791 (The Pile)

Max Activating Token Index: 709

Text #3

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1945599 (The Pile)

Max Activating Token Index: 415

Text #4

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1590485 (The Pile)

Max Activating Token Index: 297

Text #5

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.7588. Min Act: -0.0000

Data Index: 964094 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1685853 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.5899. Min Act: -0.0000

Data Index: 989837 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.6064. Min Act: -0.0000

Data Index: 1400093 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.5565. Min Act: -0.0000

Data Index: 627294 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.7014. Min Act: -0.0000

Data Index: 878605 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.5959. Min Act: -0.0000

Data Index: 147382 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.6094. Min Act: -0.0000

Data Index: 252680 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.4919. Min Act: -0.0001

Data Index: 1930195 (The Pile)

Max Activating Token Index: 792

Text #14

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.6087. Min Act: -0.0000

Data Index: 29160 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.5055. Min Act: 0.0000

Data Index: 21316 (The Pile)

Max Activating Token Index: 937

Text #16

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.5208. Min Act: -0.0000

Data Index: 339049 (The Pile)

Max Activating Token Index: 839

Text #17

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1730092 (The Pile)

Max Activating Token Index: 872

Text #18

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.5023. Min Act: -0.0000

Data Index: 201375 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 1.7121. Min Range: -1.7121

Max Act: 0.4419. Min Act: -0.0000

Data Index: 1073192 (The Pile)

Max Activating Token Index: 37