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

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

Neuron 387 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5723. Min Act: -0.0000

Data Index: 131975 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5227. Min Act: -0.0000

Data Index: 291102 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5091. Min Act: -0.0000

Data Index: 996701 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.5113. Min Act: -0.0000

Data Index: 753372 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1182300 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4159. Min Act: -0.0000

Data Index: 305092 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4335. Min Act: -0.0000

Data Index: 889012 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4112. Min Act: -0.0000

Data Index: 997039 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4254. Min Act: -0.0000

Data Index: 139739 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1057738 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4000. Min Act: -0.0000

Data Index: 624759 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4245. Min Act: -0.0000

Data Index: 36859 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.3718. Min Act: -0.0000

Data Index: 1237063 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.3820. Min Act: -0.0000

Data Index: 929943 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.4117. Min Act: -0.0000

Data Index: 828079 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.3646. Min Act: -0.0000

Data Index: 503602 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.3861. Min Act: -0.0000

Data Index: 308162 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.3521. Min Act: -0.0000

Data Index: 867148 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.3728. Min Act: -0.0000

Data Index: 613677 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.5723. Min Range: -0.5723

Max Act: 0.3333. Min Act: -0.0000

Data Index: 857199 (C4 (Web Text))

Max Activating Token Index: 904