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

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

Neuron 4533 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3995. Min Act: -0.0000

Data Index: 102879 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3686. Min Act: -0.0000

Data Index: 700765 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1135660 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3314. Min Act: -0.0000

Data Index: 677102 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1014288 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3121. Min Act: -0.0000

Data Index: 167987 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3093. Min Act: -0.0000

Data Index: 1341442 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1221884 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3130. Min Act: -0.0000

Data Index: 73034 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3327. Min Act: -0.0000

Data Index: 437877 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3023. Min Act: -0.0000

Data Index: 126746 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3192. Min Act: -0.0000

Data Index: 523330 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1210437 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1022446 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3210. Min Act: -0.0000

Data Index: 642203 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1213160 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3192. Min Act: -0.0000

Data Index: 537181 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.2958. Min Act: -0.0000

Data Index: 1237868 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1020997 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.3995. Min Range: -0.3995

Max Act: 0.2779. Min Act: -0.0000

Data Index: 664992 (C4 (Web Text))

Max Activating Token Index: 624