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

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

Neuron 3264 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.1153. Min Range: -11.1153

Max Act: 11.1153. Min Act: -0.0000

Data Index: 526587 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 11.1153. Min Range: -11.1153

Max Act: 9.1578. Min Act: -0.0000

Data Index: 440860 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 11.1153. Min Range: -11.1153

Max Act: 8.7838. Min Act: -0.0000

Data Index: 659830 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 11.1153. Min Range: -11.1153

Max Act: 7.6057. Min Act: 0.0000

Data Index: 1272088 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 11.1153. Min Range: -11.1153

Max Act: 7.3581. Min Act: -0.0000

Data Index: 1110195 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 11.1153. Min Range: -11.1153

Max Act: 6.8273. Min Act: -0.0000

Data Index: 583452 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 11.1153. Min Range: -11.1153

Max Act: 7.6549. Min Act: -0.0000

Data Index: 660086 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 11.1153. Min Range: -11.1153

Max Act: 7.3505. Min Act: -0.0000

Data Index: 1280799 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 11.1153. Min Range: -11.1153

Max Act: 7.9292. Min Act: -0.0000

Data Index: 777970 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 11.1153. Min Range: -11.1153

Max Act: 7.8215. Min Act: 0.0001

Data Index: 868117 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 11.1153. Min Range: -11.1153

Max Act: 7.2711. Min Act: -0.0000

Data Index: 70954 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 11.1153. Min Range: -11.1153

Max Act: 7.2376. Min Act: 0.0000

Data Index: 376485 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 11.1153. Min Range: -11.1153

Max Act: 6.3826. Min Act: -0.0000

Data Index: 185572 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 11.1153. Min Range: -11.1153

Max Act: 8.1912. Min Act: -0.0000

Data Index: 132401 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 11.1153. Min Range: -11.1153

Max Act: 6.9063. Min Act: -0.0000

Data Index: 908369 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 11.1153. Min Range: -11.1153

Max Act: 6.7005. Min Act: -0.0000

Data Index: 796041 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 11.1153. Min Range: -11.1153

Max Act: 6.7949. Min Act: -0.0000

Data Index: 809163 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 11.1153. Min Range: -11.1153

Max Act: 5.8015. Min Act: 0.0000

Data Index: 925819 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 11.1153. Min Range: -11.1153

Max Act: 5.9312. Min Act: -0.0000

Data Index: 510112 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 11.1153. Min Range: -11.1153

Max Act: 5.2895. Min Act: -0.0000

Data Index: 1304315 (C4 (Web Text))

Max Activating Token Index: 126