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

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

Neuron 900 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: 1.4577. Min Range: -1.4577

Max Act: 1.4577. Min Act: -0.0000

Data Index: 1285847 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.9218. Min Act: -0.0000

Data Index: 474769 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.7872. Min Act: -0.0000

Data Index: 757501 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1283919 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.7941. Min Act: -0.0000

Data Index: 430360 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.7142. Min Act: 0.0000

Data Index: 883034 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.7268. Min Act: -0.0000

Data Index: 908441 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.7657. Min Act: -0.0000

Data Index: 392284 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.6821. Min Act: -0.0000

Data Index: 640623 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.6874. Min Act: -0.0000

Data Index: 543175 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.6593. Min Act: -0.0000

Data Index: 613813 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.6558. Min Act: -0.0000

Data Index: 463792 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.6644. Min Act: -0.0000

Data Index: 1331570 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.6285. Min Act: -0.0000

Data Index: 704587 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.6031. Min Act: -0.0000

Data Index: 662107 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.5872. Min Act: -0.0000

Data Index: 971547 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.5804. Min Act: -0.0000

Data Index: 240406 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1074132 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1115457 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 1.4577. Min Range: -1.4577

Max Act: 0.5569. Min Act: -0.0000

Data Index: 695764 (C4 (Web Text))

Max Activating Token Index: 667