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

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

Neuron 1539 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1422. Min Range: -7.1422

Max Act: 7.1422. Min Act: -0.0001

Data Index: 120214 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 7.1422. Min Range: -7.1422

Max Act: 6.7706. Min Act: -0.0001

Data Index: 394182 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 7.1422. Min Range: -7.1422

Max Act: 6.5726. Min Act: -0.0001

Data Index: 925820 (C4 (Web Text))

Max Activating Token Index: 720

Text #3

Max Range: 7.1422. Min Range: -7.1422

Max Act: 6.3323. Min Act: -0.0001

Data Index: 561787 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 7.1422. Min Range: -7.1422

Max Act: 6.3289. Min Act: -0.0000

Data Index: 933121 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 7.1422. Min Range: -7.1422

Max Act: 6.4484. Min Act: -0.0000

Data Index: 1281680 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 7.1422. Min Range: -7.1422

Max Act: 6.1525. Min Act: -0.0000

Data Index: 83623 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 7.1422. Min Range: -7.1422

Max Act: 6.2890. Min Act: -0.0000

Data Index: 23382 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.8509. Min Act: -0.0000

Data Index: 280483 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.9144. Min Act: -0.0000

Data Index: 269599 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.5399. Min Act: -0.0000

Data Index: 1329984 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.5565. Min Act: -0.0000

Data Index: 991616 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.5592. Min Act: -0.0001

Data Index: 77995 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.3518. Min Act: -0.0001

Data Index: 196290 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.4724. Min Act: -0.0001

Data Index: 98807 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.3281. Min Act: -0.0001

Data Index: 1142656 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.7580. Min Act: -0.0000

Data Index: 509215 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.5417. Min Act: -0.0000

Data Index: 273023 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.6149. Min Act: -0.0000

Data Index: 677041 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 7.1422. Min Range: -7.1422

Max Act: 5.0119. Min Act: -0.0001

Data Index: 457062 (C4 (Web Text))

Max Activating Token Index: 911