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

Dataset: The Pile

Neuron 2021 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: 0.8785. Min Range: -0.8785

Max Act: 0.8785. Min Act: -0.0000

Data Index: 694236 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.6085. Min Act: -0.0000

Data Index: 918651 (The Pile)

Max Activating Token Index: 618

Text #2

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.6028. Min Act: -0.0000

Data Index: 725045 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1233813 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5790. Min Act: -0.0000

Data Index: 43150 (The Pile)

Max Activating Token Index: 625

Text #5

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1508075 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5760. Min Act: -0.0000

Data Index: 256990 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1066241 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1937152 (The Pile)

Max Activating Token Index: 902

Text #9

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.4970. Min Act: -0.0000

Data Index: 524161 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1235597 (The Pile)

Max Activating Token Index: 765

Text #11

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5099. Min Act: -0.0000

Data Index: 1416769 (The Pile)

Max Activating Token Index: 423

Text #12

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.4822. Min Act: -0.0000

Data Index: 419474 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5298. Min Act: -0.0000

Data Index: 180238 (The Pile)

Max Activating Token Index: 629

Text #14

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1658339 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1308493 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.4997. Min Act: -0.0000

Data Index: 101002 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.5182. Min Act: -0.0000

Data Index: 111554 (The Pile)

Max Activating Token Index: 851

Text #18

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1729773 (The Pile)

Max Activating Token Index: 205

Text #19

Max Range: 0.8785. Min Range: -0.8785

Max Act: 0.4494. Min Act: -0.0000

Data Index: 212915 (The Pile)

Max Activating Token Index: 998