Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4734 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4994. Min Act: 0.0000

Data Index: 647186 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4876. Min Act: -0.0000

Data Index: 636498 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4549. Min Act: -0.0000

Data Index: 276860 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4625. Min Act: -0.0000

Data Index: 189883 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4082. Min Act: -0.0000

Data Index: 741393 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1333936 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4036. Min Act: -0.0000

Data Index: 963773 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1156280 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4327. Min Act: -0.0000

Data Index: 445617 (C4 (Web Text))

Max Activating Token Index: 159

Text #9

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4279. Min Act: -0.0000

Data Index: 207922 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4122. Min Act: -0.0000

Data Index: 784453 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4151. Min Act: -0.0000

Data Index: 262102 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4229. Min Act: -0.0000

Data Index: 351865 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3840. Min Act: -0.0000

Data Index: 106227 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.4036. Min Act: -0.0000

Data Index: 450482 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3902. Min Act: -0.0000

Data Index: 985741 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3861. Min Act: -0.0000

Data Index: 112888 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3742. Min Act: -0.0000

Data Index: 424935 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3702. Min Act: -0.0000

Data Index: 185097 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.4994. Min Range: -0.4994

Max Act: 0.3910. Min Act: -0.0000

Data Index: 399134 (C4 (Web Text))

Max Activating Token Index: 384