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

Dataset: The Pile

Neuron 4440 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: 0.7806. Min Range: -0.7806

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1740295 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.7304. Min Act: -0.0000

Data Index: 247221 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1621132 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1158245 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1448259 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6438. Min Act: -0.0000

Data Index: 556894 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1815297 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1272686 (The Pile)

Max Activating Token Index: 171

Text #8

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6333. Min Act: -0.0000

Data Index: 798045 (The Pile)

Max Activating Token Index: 818

Text #9

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1577484 (The Pile)

Max Activating Token Index: 651

Text #10

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5781. Min Act: -0.0000

Data Index: 716895 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6068. Min Act: -0.0000

Data Index: 216351 (The Pile)

Max Activating Token Index: 48

Text #12

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1203462 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1756093 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.6013. Min Act: -0.0000

Data Index: 754487 (The Pile)

Max Activating Token Index: 169

Text #15

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5781. Min Act: -0.0000

Data Index: 437479 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5687. Min Act: -0.0000

Data Index: 593811 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1613932 (The Pile)

Max Activating Token Index: 239

Text #18

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5502. Min Act: -0.0000

Data Index: 1570079 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 0.7806. Min Range: -0.7806

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1890170 (The Pile)

Max Activating Token Index: 113