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

Dataset: The Pile

Neuron 1832 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.3661. Min Act: -0.0000

Data Index: 551800 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1057254 (The Pile)

Max Activating Token Index: 351

Text #2

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1303309 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2445. Min Act: -0.0000

Data Index: 329686 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2486. Min Act: -0.0000

Data Index: 476310 (The Pile)

Max Activating Token Index: 844

Text #5

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1544709 (The Pile)

Max Activating Token Index: 300

Text #6

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2217. Min Act: -0.0000

Data Index: 599259 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2197. Min Act: -0.0000

Data Index: 547510 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2178. Min Act: -0.0000

Data Index: 1000262 (The Pile)

Max Activating Token Index: 127

Text #9

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2065. Min Act: -0.0000

Data Index: 802209 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2060. Min Act: -0.0000

Data Index: 344879 (The Pile)

Max Activating Token Index: 276

Text #11

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1716480 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2357. Min Act: -0.0000

Data Index: 47707 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2229. Min Act: -0.0000

Data Index: 85041 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.1938. Min Act: -0.0000

Data Index: 934701 (The Pile)

Max Activating Token Index: 828

Text #15

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.1931. Min Act: -0.0000

Data Index: 281769 (The Pile)

Max Activating Token Index: 909

Text #16

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.2193. Min Act: -0.0000

Data Index: 470480 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.1993. Min Act: -0.0000

Data Index: 760944 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1645957 (The Pile)

Max Activating Token Index: 162

Text #19

Max Range: 0.3661. Min Range: -0.3661

Max Act: 0.1983. Min Act: -0.0000

Data Index: 541667 (The Pile)

Max Activating Token Index: 108