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

Dataset: The Pile

Neuron 2288 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: 5.0878. Min Range: -5.0878

Max Act: 5.0878. Min Act: -0.0000

Data Index: 1082033 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 5.0878. Min Range: -5.0878

Max Act: 4.6251. Min Act: -0.0000

Data Index: 934413 (The Pile)

Max Activating Token Index: 991

Text #2

Max Range: 5.0878. Min Range: -5.0878

Max Act: 4.1968. Min Act: -0.0000

Data Index: 1782810 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 5.0878. Min Range: -5.0878

Max Act: 4.0003. Min Act: -0.0000

Data Index: 1062335 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 5.0878. Min Range: -5.0878

Max Act: 4.0546. Min Act: -0.0000

Data Index: 1171691 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.5952. Min Act: -0.0000

Data Index: 1794347 (The Pile)

Max Activating Token Index: 938

Text #6

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.9357. Min Act: -0.0000

Data Index: 1494594 (The Pile)

Max Activating Token Index: 815

Text #7

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.9354. Min Act: -0.0000

Data Index: 1368337 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.7322. Min Act: -0.0000

Data Index: 834194 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.6866. Min Act: -0.0000

Data Index: 546454 (The Pile)

Max Activating Token Index: 936

Text #10

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.6185. Min Act: -0.0000

Data Index: 547257 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.7743. Min Act: -0.0000

Data Index: 91226 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.7549. Min Act: -0.0000

Data Index: 124338 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.7106. Min Act: -0.0000

Data Index: 1832435 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.6961. Min Act: -0.0000

Data Index: 179343 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.8121. Min Act: -0.0000

Data Index: 1928208 (The Pile)

Max Activating Token Index: 998

Text #16

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.6272. Min Act: -0.0000

Data Index: 1436430 (The Pile)

Max Activating Token Index: 946

Text #17

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.4628. Min Act: -0.0000

Data Index: 1768230 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.6160. Min Act: -0.0000

Data Index: 891732 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 5.0878. Min Range: -5.0878

Max Act: 3.4380. Min Act: -0.0000

Data Index: 960119 (The Pile)

Max Activating Token Index: 560