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

Dataset: The Pile

Neuron 265 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.3949. Min Act: -0.0000

Data Index: 953726 (The Pile)

Max Activating Token Index: 53

Text #1

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1403824 (The Pile)

Max Activating Token Index: 877

Text #2

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1850286 (The Pile)

Max Activating Token Index: 979

Text #3

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.1811. Min Act: -0.0000

Data Index: 1940708 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1045373 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1669683 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1285486 (The Pile)

Max Activating Token Index: 249

Text #7

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.1049. Min Act: -0.0000

Data Index: 1026259 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1628407 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.0673. Min Act: -0.0000

Data Index: 822604 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 1.4074. Min Range: -1.4074

Max Act: 1.0290. Min Act: -0.0000

Data Index: 1048963 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 1.4074. Min Range: -1.4074

Max Act: 0.9661. Min Act: -0.0000

Data Index: 1661506 (The Pile)

Max Activating Token Index: 663

Text #12

Max Range: 1.4074. Min Range: -1.4074

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1774409 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 1.4074. Min Range: -1.4074

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1247431 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 1.4074. Min Range: -1.4074

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1632102 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 1.4074. Min Range: -1.4074

Max Act: 0.9812. Min Act: -0.0000

Data Index: 139073 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 1.4074. Min Range: -1.4074

Max Act: 0.8695. Min Act: -0.0000

Data Index: 220444 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 1.4074. Min Range: -1.4074

Max Act: 0.9058. Min Act: -0.0000

Data Index: 962169 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 1.4074. Min Range: -1.4074

Max Act: 0.8990. Min Act: -0.0000

Data Index: 837444 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 1.4074. Min Range: -1.4074

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1455256 (The Pile)

Max Activating Token Index: 105