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

Dataset: The Pile

Neuron 4806 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.8211. Min Act: -0.0000

Data Index: 259897 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1035431 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1971508 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.8030. Min Act: -0.0000

Data Index: 280763 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1410634 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.8152. Min Act: -0.0000

Data Index: 651908 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1509645 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1143798 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7506. Min Act: -0.0000

Data Index: 18967 (The Pile)

Max Activating Token Index: 500

Text #9

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1125034 (The Pile)

Max Activating Token Index: 421

Text #10

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1750996 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7048. Min Act: -0.0000

Data Index: 672262 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7329. Min Act: -0.0000

Data Index: 533119 (The Pile)

Max Activating Token Index: 29

Text #13

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1007526 (The Pile)

Max Activating Token Index: 655

Text #14

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7392. Min Act: -0.0000

Data Index: 532305 (The Pile)

Max Activating Token Index: 940

Text #15

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1572988 (The Pile)

Max Activating Token Index: 868

Text #16

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6911. Min Act: -0.0000

Data Index: 189599 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1141410 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7068. Min Act: -0.0000

Data Index: 447238 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1586754 (The Pile)

Max Activating Token Index: 355