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

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

Neuron 2038 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0469. Min Range: -1.0469

Max Act: 1.0469. Min Act: -0.0000

Data Index: 558945 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9362. Min Act: -0.0000

Data Index: 563467 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9949. Min Act: -0.0000

Data Index: 19763 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9315. Min Act: -0.0000

Data Index: 1149718 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9451. Min Act: -0.0000

Data Index: 205925 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1338347 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9201. Min Act: -0.0000

Data Index: 761906 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9784. Min Act: -0.0000

Data Index: 948405 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8561. Min Act: -0.0000

Data Index: 795281 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1353711 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8895. Min Act: -0.0000

Data Index: 665302 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8414. Min Act: -0.0000

Data Index: 997738 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1057408 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8282. Min Act: -0.0000

Data Index: 296075 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8779. Min Act: -0.0000

Data Index: 210573 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.8676. Min Act: -0.0000

Data Index: 862012 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9088. Min Act: -0.0000

Data Index: 189451 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1136341 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.9033. Min Act: -0.0000

Data Index: 119048 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 1.0469. Min Range: -1.0469

Max Act: 0.7799. Min Act: -0.0000

Data Index: 334068 (C4 (Web Text))

Max Activating Token Index: 81