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

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

Neuron 913 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3616. Min Act: -0.0000

Data Index: 223256 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3456. Min Act: -0.0000

Data Index: 46706 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3332. Min Act: -0.0000

Data Index: 788671 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3226. Min Act: -0.0000

Data Index: 622327 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1043785 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1349650 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1038104 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2973. Min Act: -0.0000

Data Index: 173619 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2849. Min Act: -0.0000

Data Index: 582407 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2761. Min Act: -0.0000

Data Index: 2696 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2829. Min Act: -0.0000

Data Index: 485077 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2813. Min Act: -0.0000

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2389. Min Act: -0.0000

Data Index: 882876 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2758. Min Act: -0.0000

Data Index: 60951 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2754. Min Act: -0.0000

Data Index: 957263 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2664. Min Act: -0.0000

Data Index: 364392 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1325145 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2706. Min Act: -0.0000

Data Index: 1307433 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2588. Min Act: -0.0000

Data Index: 846824 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 0.3616. Min Range: -0.3616

Max Act: 0.2790. Min Act: -0.0000

Data Index: 87111 (C4 (Web Text))

Max Activating Token Index: 346