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

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

Neuron 5691 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.8422. Min Act: -0.0000

Data Index: 104839 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.5543. Min Act: -0.0000

Data Index: 709361 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.4871. Min Act: -0.0000

Data Index: 175346 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.4441. Min Act: -0.0000

Data Index: 719611 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.2744. Min Act: -0.0000

Data Index: 936484 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.2288. Min Act: 0.0000

Data Index: 260826 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.1442. Min Act: -0.0000

Data Index: 676495 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1055630 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.0620. Min Act: -0.0000

Data Index: 702559 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1023013 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.8422. Min Range: -1.8422

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1115750 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.0164. Min Act: -0.0000

Data Index: 87333 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.0466. Min Act: -0.0000

Data Index: 450684 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 1.8422. Min Range: -1.8422

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1281693 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.8422. Min Range: -1.8422

Max Act: 0.9285. Min Act: -0.0000

Data Index: 786488 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.8422. Min Range: -1.8422

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1268286 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 1.8422. Min Range: -1.8422

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1171147 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 1.8422. Min Range: -1.8422

Max Act: 0.9391. Min Act: -0.0000

Data Index: 192207 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.8422. Min Range: -1.8422

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1035355 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 1.8422. Min Range: -1.8422

Max Act: 0.8472. Min Act: -0.0000

Data Index: 107250 (C4 (Web Text))

Max Activating Token Index: 769