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

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

Neuron 4087 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.5073. Min Act: -0.0001

Data Index: 848033 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4578. Min Act: -0.0001

Data Index: 747595 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1392505 (Python Code)

Max Activating Token Index: 811

Text #3

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3643. Min Act: -0.0001

Data Index: 1494719 (Python Code)

Max Activating Token Index: 985

Text #4

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4572. Min Act: -0.0001

Data Index: 611257 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3794. Min Act: -0.0001

Data Index: 1405299 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4078. Min Act: -0.0001

Data Index: 378146 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3877. Min Act: -0.0001

Data Index: 1112776 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3866. Min Act: -0.0001

Data Index: 216972 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4087. Min Act: -0.0001

Data Index: 613480 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1348098 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3753. Min Act: -0.0001

Data Index: 1354452 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3348. Min Act: -0.0001

Data Index: 585146 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3635. Min Act: -0.0001

Data Index: 778289 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3595. Min Act: -0.0001

Data Index: 93851 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3816. Min Act: -0.0001

Data Index: 66496 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3698. Min Act: -0.0001

Data Index: 1088070 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3907. Min Act: -0.0001

Data Index: 745686 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.4187. Min Act: -0.0001

Data Index: 1620098 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.5073. Min Range: -0.5073

Max Act: 0.3677. Min Act: -0.0001

Data Index: 347927 (C4 (Web Text))

Max Activating Token Index: 583