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

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

Neuron 852 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: 1.7856. Min Range: -1.7856

Max Act: 1.7856. Min Act: -0.0000

Data Index: 41055 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.6851. Min Act: -0.0000

Data Index: 250994 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.3322. Min Act: -0.0000

Data Index: 630629 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.3790. Min Act: -0.0000

Data Index: 138081 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.2904. Min Act: -0.0000

Data Index: 373337 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.2536. Min Act: -0.0000

Data Index: 601048 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.0972. Min Act: -0.0000

Data Index: 744609 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.1125. Min Act: -0.0000

Data Index: 889436 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.0408. Min Act: -0.0000

Data Index: 295931 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.0130. Min Act: -0.0000

Data Index: 1140385 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1177847 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9884. Min Act: -0.0000

Data Index: 674134 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9850. Min Act: -0.0000

Data Index: 2018 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9765. Min Act: -0.0000

Data Index: 901466 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9063. Min Act: -0.0000

Data Index: 856099 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9876. Min Act: -0.0000

Data Index: 32030 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1024841 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1284464 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.8565. Min Act: -0.0000

Data Index: 429528 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.8723. Min Act: -0.0000

Data Index: 822989 (C4 (Web Text))

Max Activating Token Index: 366