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

Dataset: The Pile

Neuron 3663 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: 0.9850. Min Range: -0.9850

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1377889 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9649. Min Act: -0.0000

Data Index: 780168 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1652012 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1385699 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1095481 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1501459 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9022. Min Act: -0.0000

Data Index: 194251 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8986. Min Act: -0.0000

Data Index: 532257 (The Pile)

Max Activating Token Index: 630

Text #8

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1951328 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8591. Min Act: -0.0000

Data Index: 308815 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8114. Min Act: -0.0000

Data Index: 865831 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1705053 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7399. Min Act: -0.0000

Data Index: 253404 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7952. Min Act: -0.0000

Data Index: 924889 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7828. Min Act: -0.0000

Data Index: 1318815 (The Pile)

Max Activating Token Index: 30

Text #15

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8208. Min Act: -0.0000

Data Index: 928935 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1261017 (The Pile)

Max Activating Token Index: 69

Text #17

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1193568 (The Pile)

Max Activating Token Index: 794

Text #18

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7800. Min Act: -0.0000

Data Index: 469810 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1884028 (The Pile)

Max Activating Token Index: 337