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

Dataset: The Pile

Neuron 473 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: 0.7922. Min Range: -0.7922

Max Act: 0.7922. Min Act: -0.0000

Data Index: 713352 (The Pile)

Max Activating Token Index: 717

Text #1

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1351781 (The Pile)

Max Activating Token Index: 401

Text #2

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1208609 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1554605 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1608915 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5721. Min Act: -0.0000

Data Index: 704695 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5773. Min Act: -0.0000

Data Index: 529672 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1052299 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5645. Min Act: -0.0000

Data Index: 657418 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5750. Min Act: -0.0000

Data Index: 44015 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5228. Min Act: -0.0000

Data Index: 660149 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5403. Min Act: -0.0000

Data Index: 183122 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5180. Min Act: -0.0000

Data Index: 535910 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5123. Min Act: -0.0000

Data Index: 743417 (The Pile)

Max Activating Token Index: 909

Text #14

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1299760 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4651. Min Act: -0.0000

Data Index: 962237 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4989. Min Act: -0.0000

Data Index: 10637 (The Pile)

Max Activating Token Index: 993

Text #17

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1453883 (The Pile)

Max Activating Token Index: 294

Text #18

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1461315 (The Pile)

Max Activating Token Index: 144

Text #19

Max Range: 0.7922. Min Range: -0.7922

Max Act: 0.4364. Min Act: -0.0000

Data Index: 1658690 (The Pile)

Max Activating Token Index: 704