Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2125 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.4040. Min Act: -0.0001

Data Index: 667690 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3732. Min Act: -0.0000

Data Index: 743386 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3437. Min Act: -0.0000

Data Index: 538492 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.3069. Min Act: -0.0000

Data Index: 271774 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2880. Min Act: -0.0001

Data Index: 226677 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2801. Min Act: -0.0000

Data Index: 64986 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2757. Min Act: -0.0001

Data Index: 948838 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2803. Min Act: -0.0000

Data Index: 218554 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2793. Min Act: -0.0001

Data Index: 1023935 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2696. Min Act: -0.0001

Data Index: 268692 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2883. Min Act: -0.0001

Data Index: 638862 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2646. Min Act: -0.0001

Data Index: 485885 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2635. Min Act: -0.0000

Data Index: 794621 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2642. Min Act: -0.0001

Data Index: 737529 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2594. Min Act: -0.0000

Data Index: 765113 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2589. Min Act: -0.0000

Data Index: 783266 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2593. Min Act: -0.0001

Data Index: 287926 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2499. Min Act: -0.0000

Data Index: 843689 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2494. Min Act: -0.0000

Data Index: 156556 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.4040. Min Range: -0.4040

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1163983 (C4 (Web Text))

Max Activating Token Index: 949