Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 578 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1455. Min Range: -2.1455

Max Act: 2.0649. Min Act: -0.0000

Data Index: 727661 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 2.1455. Min Range: -2.1455

Max Act: 2.1455. Min Act: -0.0000

Data Index: 730158 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.8143. Min Act: -0.0000

Data Index: 1321725 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.8334. Min Act: -0.0000

Data Index: 365996 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.8805. Min Act: -0.0000

Data Index: 950520 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.6651. Min Act: -0.0000

Data Index: 249361 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.6643. Min Act: -0.0000

Data Index: 672762 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.5981. Min Act: -0.0000

Data Index: 300176 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1225530 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.4965. Min Act: -0.0000

Data Index: 1019128 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.5684. Min Act: -0.0000

Data Index: 272967 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.5953. Min Act: -0.0000

Data Index: 872908 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1227176 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.4766. Min Act: -0.0000

Data Index: 1239479 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.5589. Min Act: -0.0000

Data Index: 74148 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.4556. Min Act: -0.0000

Data Index: 695412 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.4850. Min Act: -0.0000

Data Index: 87827 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.3985. Min Act: -0.0000

Data Index: 247255 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.4710. Min Act: -0.0000

Data Index: 1302237 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 2.1455. Min Range: -2.1455

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1286465 (C4 (Web Text))

Max Activating Token Index: 1004