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

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

Neuron 4166 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.4117. Min Act: -0.0000

Data Index: 771883 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1268392 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3669. Min Act: -0.0000

Data Index: 704053 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3766. Min Act: -0.0000

Data Index: 459527 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3473. Min Act: -0.0000

Data Index: 66926 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1277234 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3391. Min Act: -0.0000

Data Index: 1238145 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3469. Min Act: -0.0000

Data Index: 469462 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1332783 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3391. Min Act: -0.0000

Data Index: 890278 (C4 (Web Text))

Max Activating Token Index: 902

Text #10

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3314. Min Act: -0.0000

Data Index: 42672 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3131. Min Act: -0.0000

Data Index: 961513 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3238. Min Act: -0.0000

Data Index: 655842 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3151. Min Act: -0.0000

Data Index: 770170 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3222. Min Act: -0.0000

Data Index: 112348 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3023. Min Act: -0.0000

Data Index: 516915 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3013. Min Act: -0.0000

Data Index: 999509 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3112. Min Act: -0.0000

Data Index: 444998 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1241156 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.4117. Min Range: -0.4117

Max Act: 0.3087. Min Act: -0.0000

Data Index: 714177 (C4 (Web Text))

Max Activating Token Index: 70