Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 396 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 13.1455. Min Range: -13.1455

Max Act: 13.1455. Min Act: -0.0001

Data Index: 86207 (The Pile)

Max Activating Token Index: 160

Text #1

Max Range: 13.1455. Min Range: -13.1455

Max Act: 0.6103. Min Act: -0.0000

Data Index: 864541 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 13.1455. Min Range: -13.1455

Max Act: 0.0811. Min Act: -0.0000

Data Index: 131092 (The Pile)

Max Activating Token Index: 692

Text #3

Max Range: 13.1455. Min Range: -13.1455

Max Act: 12.2689. Min Act: -0.0000

Data Index: 954232 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 13.1455. Min Range: -13.1455

Max Act: 9.0595. Min Act: -0.0000

Data Index: 1965108 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 13.1455. Min Range: -13.1455

Max Act: 7.7911. Min Act: -0.0000

Data Index: 1764422 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 13.1455. Min Range: -13.1455

Max Act: 8.9099. Min Act: -0.0001

Data Index: 1697703 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 13.1455. Min Range: -13.1455

Max Act: 3.6601. Min Act: -0.0000

Data Index: 1912825 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 13.1455. Min Range: -13.1455

Max Act: 11.6804. Min Act: -0.0000

Data Index: 557042 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 13.1455. Min Range: -13.1455

Max Act: 2.4013. Min Act: -0.0000

Data Index: 1925448 (The Pile)

Max Activating Token Index: 215

Text #10

Max Range: 13.1455. Min Range: -13.1455

Max Act: 2.3907. Min Act: -0.0000

Data Index: 570051 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 13.1455. Min Range: -13.1455

Max Act: 2.1029. Min Act: -0.0000

Data Index: 1845423 (The Pile)

Max Activating Token Index: 623

Text #12

Max Range: 13.1455. Min Range: -13.1455

Max Act: 2.0163. Min Act: -0.0000

Data Index: 104286 (The Pile)

Max Activating Token Index: 587

Text #13

Max Range: 13.1455. Min Range: -13.1455

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1713132 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 13.1455. Min Range: -13.1455

Max Act: 1.4042. Min Act: -0.0000

Data Index: 1049110 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 13.1455. Min Range: -13.1455

Max Act: 1.3100. Min Act: -0.0001

Data Index: 909719 (The Pile)

Max Activating Token Index: 267

Text #16

Max Range: 13.1455. Min Range: -13.1455

Max Act: 1.5324. Min Act: -0.0000

Data Index: 1969338 (The Pile)

Max Activating Token Index: 427

Text #17

Max Range: 13.1455. Min Range: -13.1455

Max Act: 1.1072. Min Act: -0.0000

Data Index: 802366 (The Pile)

Max Activating Token Index: 259

Text #18

Max Range: 13.1455. Min Range: -13.1455

Max Act: 1.5228. Min Act: -0.0001

Data Index: 631881 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 13.1455. Min Range: -13.1455

Max Act: 1.0014. Min Act: -0.0000

Data Index: 122957 (The Pile)

Max Activating Token Index: 855