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

Dataset: The Pile

Neuron 4909 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: 0.4855. Min Range: -0.4855

Max Act: 0.4855. Min Act: -0.0000

Data Index: 1209882 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4827. Min Act: -0.0000

Data Index: 862352 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4403. Min Act: -0.0000

Data Index: 286433 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4578. Min Act: -0.0000

Data Index: 774858 (The Pile)

Max Activating Token Index: 1021

Text #4

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1315485 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4549. Min Act: -0.0000

Data Index: 99891 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1313372 (The Pile)

Max Activating Token Index: 640

Text #7

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1138862 (The Pile)

Max Activating Token Index: 661

Text #8

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4506. Min Act: -0.0000

Data Index: 664988 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1500922 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1385457 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1754627 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3930. Min Act: -0.0000

Data Index: 714583 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3755. Min Act: -0.0000

Data Index: 1021635 (The Pile)

Max Activating Token Index: 46

Text #14

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4017. Min Act: -0.0000

Data Index: 398340 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1697173 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.4215. Min Act: -0.0000

Data Index: 904015 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1525475 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1127689 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 0.4855. Min Range: -0.4855

Max Act: 0.3887. Min Act: -0.0000

Data Index: 258649 (The Pile)

Max Activating Token Index: 273