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

Dataset: The Pile

Neuron 1780 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5844. Min Act: -0.0000

Data Index: 1353977 (The Pile)

Max Activating Token Index: 873

Text #1

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1465651 (The Pile)

Max Activating Token Index: 532

Text #2

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5775. Min Act: -0.0000

Data Index: 101835 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1992496 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5203. Min Act: -0.0000

Data Index: 776282 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5431. Min Act: -0.0000

Data Index: 1663803 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5067. Min Act: -0.0000

Data Index: 722944 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1889721 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4826. Min Act: -0.0000

Data Index: 191938 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1297510 (The Pile)

Max Activating Token Index: 532

Text #10

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4887. Min Act: -0.0000

Data Index: 618186 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1667274 (The Pile)

Max Activating Token Index: 431

Text #12

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4323. Min Act: -0.0000

Data Index: 1215538 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4355. Min Act: -0.0000

Data Index: 813431 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4290. Min Act: -0.0000

Data Index: 742354 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4265. Min Act: -0.0000

Data Index: 287689 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1859209 (The Pile)

Max Activating Token Index: 511

Text #17

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4113. Min Act: -0.0000

Data Index: 1244010 (The Pile)

Max Activating Token Index: 172

Text #18

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4190. Min Act: -0.0000

Data Index: 570648 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.5844. Min Range: -0.5844

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1172650 (The Pile)

Max Activating Token Index: 592