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

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

Neuron 4004 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9789. Min Range: -5.9789

Max Act: 5.9789. Min Act: -0.0000

Data Index: 334925 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 5.9789. Min Range: -5.9789

Max Act: 5.2671. Min Act: -0.0000

Data Index: 489503 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 5.9789. Min Range: -5.9789

Max Act: 5.3545. Min Act: -0.0000

Data Index: 143771 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 5.9789. Min Range: -5.9789

Max Act: 5.4964. Min Act: -0.0000

Data Index: 946970 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 5.9789. Min Range: -5.9789

Max Act: 5.0697. Min Act: -0.0000

Data Index: 144561 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 5.9789. Min Range: -5.9789

Max Act: 5.0348. Min Act: -0.0000

Data Index: 371268 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 5.9789. Min Range: -5.9789

Max Act: 5.2068. Min Act: -0.0000

Data Index: 958167 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 5.9789. Min Range: -5.9789

Max Act: 5.2020. Min Act: -0.0000

Data Index: 89688 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.5733. Min Act: -0.0000

Data Index: 1020569 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.9130. Min Act: -0.0000

Data Index: 299035 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 5.9789. Min Range: -5.9789

Max Act: 5.0821. Min Act: -0.0000

Data Index: 1192143 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.8628. Min Act: -0.0000

Data Index: 368024 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.6873. Min Act: -0.0000

Data Index: 833123 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.8487. Min Act: -0.0000

Data Index: 713778 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.4735. Min Act: -0.0000

Data Index: 843871 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.3191. Min Act: -0.0000

Data Index: 1261678 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.8111. Min Act: -0.0000

Data Index: 494866 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.8215. Min Act: -0.0000

Data Index: 992902 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.9774. Min Act: -0.0000

Data Index: 136832 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 5.9789. Min Range: -5.9789

Max Act: 4.4621. Min Act: -0.0000

Data Index: 91407 (C4 (Web Text))

Max Activating Token Index: 60