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

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

Neuron 1854 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2422. Min Range: -4.2422

Max Act: 4.2422. Min Act: -0.0000

Data Index: 493541 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 4.2422. Min Range: -4.2422

Max Act: 4.1245. Min Act: -0.0000

Data Index: 613909 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 4.2422. Min Range: -4.2422

Max Act: 3.8982. Min Act: -0.0000

Data Index: 75014 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 4.2422. Min Range: -4.2422

Max Act: 3.2090. Min Act: -0.0000

Data Index: 1129653 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.3512. Min Act: -0.0000

Data Index: 809862 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.3126. Min Act: -0.0000

Data Index: 1308857 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.1152. Min Act: -0.0000

Data Index: 819113 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.3320. Min Act: -0.0000

Data Index: 141727 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.1914. Min Act: -0.0000

Data Index: 594549 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.0766. Min Act: -0.0000

Data Index: 680794 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.1342. Min Act: -0.0000

Data Index: 109347 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.1057. Min Act: -0.0000

Data Index: 1348188 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.0708. Min Act: -0.0000

Data Index: 669272 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 4.2422. Min Range: -4.2422

Max Act: 1.9320. Min Act: -0.0000

Data Index: 550769 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 4.2422. Min Range: -4.2422

Max Act: 2.0138. Min Act: -0.0000

Data Index: 914608 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 4.2422. Min Range: -4.2422

Max Act: 1.9030. Min Act: -0.0000

Data Index: 876814 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 4.2422. Min Range: -4.2422

Max Act: 1.8957. Min Act: -0.0000

Data Index: 339260 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 4.2422. Min Range: -4.2422

Max Act: 1.9008. Min Act: -0.0000

Data Index: 1229832 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 4.2422. Min Range: -4.2422

Max Act: 1.9842. Min Act: -0.0000

Data Index: 358398 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 4.2422. Min Range: -4.2422

Max Act: 1.9661. Min Act: -0.0000

Data Index: 332320 (C4 (Web Text))

Max Activating Token Index: 38