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

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

Neuron 2131 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1054924 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1157054 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6117. Min Act: -0.0000

Data Index: 12400 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6124. Min Act: -0.0000

Data Index: 462735 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5915. Min Act: -0.0000

Data Index: 903310 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5550. Min Act: -0.0000

Data Index: 103652 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5848. Min Act: -0.0000

Data Index: 943767 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6018. Min Act: -0.0000

Data Index: 176879 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1175231 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1055169 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5723. Min Act: -0.0000

Data Index: 414877 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5874. Min Act: -0.0000

Data Index: 1175501 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1100151 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5228. Min Act: -0.0000

Data Index: 205094 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5761. Min Act: -0.0000

Data Index: 14952 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5816. Min Act: -0.0000

Data Index: 864908 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5607. Min Act: -0.0000

Data Index: 787137 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5417. Min Act: -0.0000

Data Index: 332630 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5366. Min Act: -0.0000

Data Index: 258685 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.6985. Min Range: -0.6985

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1313231 (C4 (Web Text))

Max Activating Token Index: 312