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

Dataset: The Pile

Neuron 1130 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1932308 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1698066 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7680. Min Act: -0.0000

Data Index: 1710679 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1225357 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6323. Min Act: -0.0000

Data Index: 971815 (The Pile)

Max Activating Token Index: 277

Text #5

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5990. Min Act: -0.0000

Data Index: 587397 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6256. Min Act: -0.0000

Data Index: 178014 (The Pile)

Max Activating Token Index: 660

Text #7

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1185065 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5928. Min Act: -0.0000

Data Index: 323851 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6503. Min Act: -0.0000

Data Index: 788293 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1256978 (The Pile)

Max Activating Token Index: 499

Text #11

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1024188 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1165298 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6010. Min Act: -0.0000

Data Index: 477063 (The Pile)

Max Activating Token Index: 589

Text #14

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6529. Min Act: -0.0000

Data Index: 1666481 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5647. Min Act: -0.0000

Data Index: 375017 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1200100 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5891. Min Act: -0.0000

Data Index: 167023 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1210399 (The Pile)

Max Activating Token Index: 757

Text #19

Max Range: 0.8477. Min Range: -0.8477

Max Act: 0.6132. Min Act: -0.0000

Data Index: 531578 (The Pile)

Max Activating Token Index: 542