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

Dataset: The Pile

Neuron 4755 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: 0.9044. Min Range: -0.9044

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1387787 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1466391 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1582031 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8379. Min Act: -0.0000

Data Index: 1878102 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8185. Min Act: -0.0000

Data Index: 478052 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1493593 (The Pile)

Max Activating Token Index: 555

Text #6

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1313795 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7411. Min Act: -0.0000

Data Index: 486210 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1286048 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.6944. Min Act: -0.0000

Data Index: 319192 (The Pile)

Max Activating Token Index: 390

Text #10

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.6885. Min Act: -0.0000

Data Index: 921433 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7111. Min Act: -0.0000

Data Index: 518394 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.6725. Min Act: -0.0000

Data Index: 1371786 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1285029 (The Pile)

Max Activating Token Index: 91

Text #14

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.6594. Min Act: -0.0000

Data Index: 340399 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1032450 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1892504 (The Pile)

Max Activating Token Index: 541

Text #17

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1257860 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.6115. Min Act: -0.0000

Data Index: 168511 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.9044. Min Range: -0.9044

Max Act: 0.5825. Min Act: -0.0000

Data Index: 312984 (The Pile)

Max Activating Token Index: 668