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

Dataset: The Pile

Neuron 2032 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.8870. Min Act: -0.0000

Data Index: 1122198 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.0889. Min Act: -0.0000

Data Index: 1780996 (The Pile)

Max Activating Token Index: 923

Text #2

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.2335. Min Act: -0.0000

Data Index: 1292188 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.1910. Min Act: -0.0000

Data Index: 1827274 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.3162. Min Act: -0.0000

Data Index: 763931 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.0792. Min Act: -0.0000

Data Index: 893499 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.9267. Min Act: -0.0000

Data Index: 1575620 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.1817. Min Act: -0.0000

Data Index: 599644 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 3.8870. Min Range: -3.8870

Max Act: 3.0110. Min Act: -0.0000

Data Index: 1288756 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.7477. Min Act: -0.0000

Data Index: 1134466 (The Pile)

Max Activating Token Index: 987

Text #10

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.5916. Min Act: -0.0000

Data Index: 578953 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.8707. Min Act: -0.0000

Data Index: 1693437 (The Pile)

Max Activating Token Index: 272

Text #12

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.8274. Min Act: -0.0000

Data Index: 1775004 (The Pile)

Max Activating Token Index: 4

Text #13

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.5230. Min Act: -0.0000

Data Index: 1458632 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.3754. Min Act: -0.0000

Data Index: 640692 (The Pile)

Max Activating Token Index: 648

Text #15

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.6374. Min Act: -0.0000

Data Index: 620496 (The Pile)

Max Activating Token Index: 34

Text #16

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.6000. Min Act: -0.0000

Data Index: 431125 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.8255. Min Act: -0.0000

Data Index: 1248204 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.6774. Min Act: -0.0000

Data Index: 1105307 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 3.8870. Min Range: -3.8870

Max Act: 2.4211. Min Act: -0.0000

Data Index: 1623687 (The Pile)

Max Activating Token Index: 238