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

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

Neuron 4198 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5728. Min Range: -3.5728

Max Act: 3.5728. Min Act: -0.0000

Data Index: 750162 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 3.5728. Min Range: -3.5728

Max Act: 3.1473. Min Act: -0.0000

Data Index: 522539 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.8201. Min Act: -0.0000

Data Index: 105733 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.9897. Min Act: -0.0000

Data Index: 187137 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.9806. Min Act: -0.0000

Data Index: 617446 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.8400. Min Act: -0.0000

Data Index: 1129391 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.9002. Min Act: -0.0000

Data Index: 269830 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 3.5728. Min Range: -3.5728

Max Act: 3.0454. Min Act: -0.0000

Data Index: 580103 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.8498. Min Act: -0.0000

Data Index: 1002329 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.6632. Min Act: -0.0000

Data Index: 1328536 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.9352. Min Act: -0.0000

Data Index: 1055012 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.6533. Min Act: -0.0000

Data Index: 1075365 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.6194. Min Act: -0.0000

Data Index: 1306625 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.6367. Min Act: -0.0000

Data Index: 364487 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.6240. Min Act: -0.0000

Data Index: 626790 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.8589. Min Act: -0.0000

Data Index: 330432 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.5648. Min Act: -0.0000

Data Index: 26193 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.6784. Min Act: -0.0000

Data Index: 727682 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.2764. Min Act: -0.0000

Data Index: 1082896 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 3.5728. Min Range: -3.5728

Max Act: 2.6648. Min Act: -0.0000

Data Index: 847453 (C4 (Web Text))

Max Activating Token Index: 366