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

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

Neuron 2646 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: 0.7268. Min Range: -0.7268

Max Act: 0.6564. Min Act: -0.0001

Data Index: 1111865 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5534. Min Act: -0.0001

Data Index: 1054368 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.7268. Min Act: -0.0001

Data Index: 89339 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4982. Min Act: -0.0001

Data Index: 433881 (C4 (Web Text))

Max Activating Token Index: 976

Text #4

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4736. Min Act: -0.0000

Data Index: 407013 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4975. Min Act: -0.0001

Data Index: 311946 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5101. Min Act: -0.0001

Data Index: 757290 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5316. Min Act: -0.0001

Data Index: 637758 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5149. Min Act: -0.0001

Data Index: 1242749 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4916. Min Act: -0.0001

Data Index: 192462 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4986. Min Act: -0.0001

Data Index: 463658 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4906. Min Act: -0.0000

Data Index: 984408 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.5666. Min Act: -0.0001

Data Index: 1022375 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4825. Min Act: -0.0001

Data Index: 1241110 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4437. Min Act: -0.0001

Data Index: 813372 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4366. Min Act: -0.0001

Data Index: 1342888 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4006. Min Act: -0.0001

Data Index: 339026 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4320. Min Act: -0.0001

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.4238. Min Act: -0.0001

Data Index: 902764 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.7268. Min Range: -0.7268

Max Act: 0.3919. Min Act: -0.0001

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 877