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

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

Neuron 3277 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: 0.4246. Min Range: -0.4246

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1025155 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1214212 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3346. Min Act: -0.0000

Data Index: 120969 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2762. Min Act: -0.0000

Data Index: 983367 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3047. Min Act: -0.0000

Data Index: 485164 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1282086 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1238235 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2906. Min Act: -0.0000

Data Index: 966469 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1285320 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2797. Min Act: -0.0000

Data Index: 913623 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2794. Min Act: -0.0000

Data Index: 448605 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1357413 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2746. Min Act: -0.0000

Data Index: 435978 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2752. Min Act: -0.0000

Data Index: 122305 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1100440 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2838. Min Act: -0.0000

Data Index: 342826 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2647. Min Act: -0.0000

Data Index: 569197 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2769. Min Act: -0.0000

Data Index: 888977 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1318705 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.4246. Min Range: -0.4246

Max Act: 0.2549. Min Act: -0.0000

Data Index: 930774 (C4 (Web Text))

Max Activating Token Index: 398