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

Dataset: The Pile

Neuron 409 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: 4.5234. Min Range: -4.5234

Max Act: 4.4907. Min Act: -0.0000

Data Index: 1628269 (The Pile)

Max Activating Token Index: 420

Text #1

Max Range: 4.5234. Min Range: -4.5234

Max Act: 4.5234. Min Act: -0.0000

Data Index: 397681 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 4.5234. Min Range: -4.5234

Max Act: 4.1264. Min Act: -0.0000

Data Index: 1951642 (The Pile)

Max Activating Token Index: 364

Text #3

Max Range: 4.5234. Min Range: -4.5234

Max Act: 4.0225. Min Act: -0.0000

Data Index: 1948747 (The Pile)

Max Activating Token Index: 259

Text #4

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.6841. Min Act: -0.0000

Data Index: 1332670 (The Pile)

Max Activating Token Index: 247

Text #5

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.7398. Min Act: -0.0000

Data Index: 865395 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.7063. Min Act: -0.0000

Data Index: 450134 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.4877. Min Act: -0.0000

Data Index: 1814771 (The Pile)

Max Activating Token Index: 60

Text #8

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.2591. Min Act: -0.0000

Data Index: 711391 (The Pile)

Max Activating Token Index: 507

Text #9

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.2401. Min Act: -0.0000

Data Index: 1341673 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.3366. Min Act: -0.0000

Data Index: 1123944 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.1158. Min Act: -0.0000

Data Index: 49525 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.0858. Min Act: -0.0000

Data Index: 971523 (The Pile)

Max Activating Token Index: 645

Text #13

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.2055. Min Act: -0.0000

Data Index: 1764391 (The Pile)

Max Activating Token Index: 65

Text #14

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.0099. Min Act: -0.0000

Data Index: 1761989 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 4.5234. Min Range: -4.5234

Max Act: 2.9501. Min Act: -0.0000

Data Index: 580129 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 4.5234. Min Range: -4.5234

Max Act: 2.7838. Min Act: -0.0000

Data Index: 1989848 (The Pile)

Max Activating Token Index: 62

Text #17

Max Range: 4.5234. Min Range: -4.5234

Max Act: 3.0687. Min Act: -0.0000

Data Index: 1710399 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 4.5234. Min Range: -4.5234

Max Act: 2.7412. Min Act: -0.0000

Data Index: 1596448 (The Pile)

Max Activating Token Index: 128

Text #19

Max Range: 4.5234. Min Range: -4.5234

Max Act: 2.8130. Min Act: -0.0000

Data Index: 61878 (The Pile)

Max Activating Token Index: 217