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

Dataset: The Pile

Neuron 1720 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.3866. Min Act: -0.0000

Data Index: 488833 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.1711. Min Act: -0.0000

Data Index: 523330 (The Pile)

Max Activating Token Index: 592

Text #2

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1250827 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.0805. Min Act: -0.0000

Data Index: 976333 (The Pile)

Max Activating Token Index: 252

Text #4

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.0180. Min Act: -0.0000

Data Index: 1351829 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1821975 (The Pile)

Max Activating Token Index: 968

Text #6

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1266798 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.0532. Min Act: -0.0000

Data Index: 419596 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1870597 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8504. Min Act: -0.0000

Data Index: 899698 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9551. Min Act: -0.0000

Data Index: 1123434 (The Pile)

Max Activating Token Index: 412

Text #11

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9401. Min Act: -0.0000

Data Index: 905597 (The Pile)

Max Activating Token Index: 808

Text #12

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1990810 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1166532 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1975803 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9277. Min Act: -0.0000

Data Index: 140734 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1746224 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9309. Min Act: -0.0000

Data Index: 930190 (The Pile)

Max Activating Token Index: 447

Text #18

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8175. Min Act: -0.0000

Data Index: 518414 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1576852 (The Pile)

Max Activating Token Index: 908