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

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

Neuron 738 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 15.2693. Min Range: -15.2693

Max Act: 15.2693. Min Act: -0.0002

Data Index: 1612868 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 15.2693. Min Range: -15.2693

Max Act: 7.5536. Min Act: -0.0002

Data Index: 1262428 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 15.2693. Min Range: -15.2693

Max Act: 5.2798. Min Act: -0.0002

Data Index: 825266 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 15.2693. Min Range: -15.2693

Max Act: 4.7507. Min Act: -0.0002

Data Index: 847224 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 15.2693. Min Range: -15.2693

Max Act: 4.4430. Min Act: -0.0002

Data Index: 767889 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 15.2693. Min Range: -15.2693

Max Act: 4.3648. Min Act: -0.0002

Data Index: 25767 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 15.2693. Min Range: -15.2693

Max Act: 4.1031. Min Act: -0.0002

Data Index: 158996 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.9905. Min Act: -0.0001

Data Index: 313898 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.9846. Min Act: -0.0002

Data Index: 887287 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.8634. Min Act: -0.0002

Data Index: 1208504 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.6692. Min Act: -0.0003

Data Index: 146917 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.6107. Min Act: -0.0002

Data Index: 784809 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.6007. Min Act: -0.0002

Data Index: 355287 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.5062. Min Act: -0.0002

Data Index: 818904 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.5697. Min Act: -0.0002

Data Index: 868734 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.4811. Min Act: -0.0003

Data Index: 482424 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.4819. Min Act: -0.0003

Data Index: 548397 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.3130. Min Act: -0.0002

Data Index: 585788 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.2933. Min Act: -0.0002

Data Index: 1148192 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 15.2693. Min Range: -15.2693

Max Act: 3.3612. Min Act: -0.0002

Data Index: 1053103 (C4 (Web Text))

Max Activating Token Index: 742