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

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

Neuron 3086 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.8284. Min Act: -0.0000

Data Index: 165541 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.8537. Min Act: -0.0000

Data Index: 741981 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.7300. Min Act: -0.0000

Data Index: 93722 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6976. Min Act: -0.0000

Data Index: 797545 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1132215 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6497. Min Act: -0.0000

Data Index: 337525 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6656. Min Act: -0.0000

Data Index: 1179572 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6054. Min Act: -0.0000

Data Index: 525289 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6077. Min Act: -0.0000

Data Index: 1042011 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1189511 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1096202 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5926. Min Act: -0.0000

Data Index: 900367 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5178. Min Act: -0.0000

Data Index: 664707 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5892. Min Act: -0.0001

Data Index: 1007514 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5463. Min Act: -0.0000

Data Index: 232901 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6224. Min Act: -0.0000

Data Index: 2354 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5773. Min Act: -0.0000

Data Index: 795246 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1175075 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5386. Min Act: -0.0000

Data Index: 368372 (C4 (Web Text))

Max Activating Token Index: 84

Text #19

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1254539 (C4 (Web Text))

Max Activating Token Index: 796