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

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

Neuron 3442 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4996. Min Act: -0.0001

Data Index: 255087 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4361. Min Act: -0.0001

Data Index: 341096 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4424. Min Act: -0.0001

Data Index: 208227 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4260. Min Act: -0.0001

Data Index: 612218 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4417. Min Act: -0.0001

Data Index: 41043 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4265. Min Act: -0.0001

Data Index: 592114 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4118. Min Act: -0.0001

Data Index: 1207924 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3925. Min Act: -0.0001

Data Index: 1333091 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3905. Min Act: -0.0001

Data Index: 924072 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3929. Min Act: -0.0001

Data Index: 683786 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3870. Min Act: -0.0001

Data Index: 933690 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3861. Min Act: -0.0001

Data Index: 932781 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3796. Min Act: -0.0001

Data Index: 826881 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3651. Min Act: -0.0001

Data Index: 75994 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3615. Min Act: -0.0001

Data Index: 500108 (C4 (Web Text))

Max Activating Token Index: 939

Text #15

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3183. Min Act: -0.0001

Data Index: 139624 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3143. Min Act: -0.0001

Data Index: 308633 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3096. Min Act: -0.0001

Data Index: 1135551 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2739. Min Act: -0.0001

Data Index: 244784 (C4 (Web Text))

Max Activating Token Index: 787

Text #19

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.2691. Min Act: -0.0001

Data Index: 279593 (C4 (Web Text))

Max Activating Token Index: 822