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

Dataset: The Pile

Neuron 4382 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.4672. Min Act: -0.0000

Data Index: 1501819 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1573782 (The Pile)

Max Activating Token Index: 901

Text #2

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1360616 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1781957 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.3680. Min Act: -0.0000

Data Index: 247351 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.2253. Min Act: -0.0000

Data Index: 704939 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1209. Min Act: -0.0000

Data Index: 39539 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1483536 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1783703 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1233. Min Act: -0.0000

Data Index: 761953 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0903. Min Act: -0.0000

Data Index: 1178642 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0892. Min Act: -0.0000

Data Index: 125474 (The Pile)

Max Activating Token Index: 300

Text #12

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1167. Min Act: -0.0000

Data Index: 1259138 (The Pile)

Max Activating Token Index: 510

Text #13

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0419. Min Act: -0.0000

Data Index: 1391330 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.1644. Min Act: -0.0000

Data Index: 1481421 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0833. Min Act: -0.0000

Data Index: 27140 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0897. Min Act: -0.0000

Data Index: 758021 (The Pile)

Max Activating Token Index: 165

Text #17

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0856. Min Act: -0.0000

Data Index: 122908 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0769. Min Act: 0.0000

Data Index: 1974489 (The Pile)

Max Activating Token Index: 171

Text #19

Max Range: 1.4672. Min Range: -1.4672

Max Act: 1.0694. Min Act: -0.0000

Data Index: 326334 (The Pile)

Max Activating Token Index: 442