Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1200 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3741. Min Act: -0.0001

Data Index: 401128 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3316. Min Act: -0.0001

Data Index: 694469 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3325. Min Act: -0.0000

Data Index: 875756 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3380. Min Act: -0.0001

Data Index: 167454 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3387. Min Act: -0.0000

Data Index: 453335 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3575. Min Act: -0.0000

Data Index: 88825 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3307. Min Act: -0.0001

Data Index: 524483 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3209. Min Act: -0.0001

Data Index: 588081 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1217231 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3087. Min Act: -0.0001

Data Index: 19084 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3348. Min Act: -0.0001

Data Index: 602142 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3171. Min Act: -0.0001

Data Index: 75878 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2918. Min Act: -0.0001

Data Index: 941879 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.3077. Min Act: -0.0001

Data Index: 267860 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2932. Min Act: -0.0001

Data Index: 785689 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2581. Min Act: -0.0001

Data Index: 249564 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1142973 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2179. Min Act: -0.0001

Data Index: 787263 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.2105. Min Act: -0.0001

Data Index: 977109 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.3741. Min Range: -0.3741

Max Act: 0.1997. Min Act: -0.0001

Data Index: 295455 (C4 (Web Text))

Max Activating Token Index: 670