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

Dataset: The Pile

Neuron 3309 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: 3.8292. Min Range: -3.8292

Max Act: 3.8292. Min Act: -0.0000

Data Index: 1795657 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.5902. Min Act: -0.0000

Data Index: 561325 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.5719. Min Act: -0.0000

Data Index: 1056890 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.7071. Min Act: -0.0000

Data Index: 1603623 (The Pile)

Max Activating Token Index: 870

Text #4

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.3059. Min Act: -0.0000

Data Index: 1577126 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.5225. Min Act: -0.0000

Data Index: 1855632 (The Pile)

Max Activating Token Index: 987

Text #6

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.5942. Min Act: -0.0000

Data Index: 1771899 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.3724. Min Act: -0.0000

Data Index: 570051 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.3745. Min Act: -0.0000

Data Index: 1228107 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.2015. Min Act: -0.0000

Data Index: 1271980 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.3610. Min Act: -0.0000

Data Index: 486836 (The Pile)

Max Activating Token Index: 371

Text #11

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.3808. Min Act: -0.0000

Data Index: 846638 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.4936. Min Act: -0.0000

Data Index: 1096906 (The Pile)

Max Activating Token Index: 552

Text #13

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.3240. Min Act: -0.0000

Data Index: 1835029 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.1118. Min Act: -0.0000

Data Index: 863811 (The Pile)

Max Activating Token Index: 319

Text #15

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.1092. Min Act: -0.0000

Data Index: 1093900 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.2659. Min Act: -0.0000

Data Index: 6579 (The Pile)

Max Activating Token Index: 956

Text #17

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.1001. Min Act: -0.0000

Data Index: 1765327 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 3.8292. Min Range: -3.8292

Max Act: 3.2579. Min Act: -0.0000

Data Index: 75491 (The Pile)

Max Activating Token Index: 601

Text #19

Max Range: 3.8292. Min Range: -3.8292

Max Act: 2.9475. Min Act: -0.0000

Data Index: 616416 (The Pile)

Max Activating Token Index: 843