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

Dataset: The Pile

Neuron 4844 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.9626. Min Act: -0.0000

Data Index: 462303 (The Pile)

Max Activating Token Index: 767

Text #1

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.6847. Min Act: -0.0000

Data Index: 21464 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1422111 (The Pile)

Max Activating Token Index: 140

Text #3

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1393929 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5484. Min Act: -0.0000

Data Index: 1411594 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5573. Min Act: -0.0000

Data Index: 9975 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5602. Min Act: -0.0000

Data Index: 784772 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1168283 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1138741 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1827339 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5460. Min Act: -0.0000

Data Index: 202475 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5100. Min Act: -0.0000

Data Index: 49497 (The Pile)

Max Activating Token Index: 284

Text #12

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.4891. Min Act: -0.0000

Data Index: 494552 (The Pile)

Max Activating Token Index: 553

Text #13

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.4933. Min Act: -0.0000

Data Index: 755837 (The Pile)

Max Activating Token Index: 974

Text #14

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5185. Min Act: -0.0000

Data Index: 257006 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5006. Min Act: -0.0000

Data Index: 183234 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5059. Min Act: -0.0000

Data Index: 289258 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.5057. Min Act: -0.0000

Data Index: 988392 (The Pile)

Max Activating Token Index: 474

Text #18

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1508961 (The Pile)

Max Activating Token Index: 637

Text #19

Max Range: 0.9626. Min Range: -0.9626

Max Act: 0.4284. Min Act: -0.0000

Data Index: 1116655 (The Pile)

Max Activating Token Index: 848