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

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

Neuron 727 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: 0.7086. Min Range: -0.7086

Max Act: 0.7086. Min Act: -0.0000

Data Index: 1103720 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1253470 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.6916. Min Act: -0.0000

Data Index: 758907 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5714. Min Act: -0.0000

Data Index: 705293 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5433. Min Act: -0.0000

Data Index: 34415 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5149. Min Act: -0.0000

Data Index: 932897 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5285. Min Act: -0.0000

Data Index: 16168 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5445. Min Act: -0.0000

Data Index: 1045484 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5395. Min Act: -0.0000

Data Index: 397613 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5118. Min Act: -0.0000

Data Index: 962024 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.5114. Min Act: -0.0000

Data Index: 453141 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1240163 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4761. Min Act: -0.0000

Data Index: 116271 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4553. Min Act: -0.0000

Data Index: 357959 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1096690 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1151596 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4571. Min Act: -0.0000

Data Index: 800779 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1317472 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.4695. Min Act: -0.0000

Data Index: 153696 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 0.7086. Min Range: -0.7086

Max Act: 0.3977. Min Act: -0.0000

Data Index: 502277 (C4 (Web Text))

Max Activating Token Index: 744