Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0542. Min Range: -1.0542

Max Act: 1.0542. Min Act: -0.0000

Data Index: 700921 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.9989. Min Act: -0.0000

Data Index: 1222093 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.8239. Min Act: -0.0000

Data Index: 143661 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.7615. Min Act: -0.0000

Data Index: 876034 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6684. Min Act: -0.0000

Data Index: 945828 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1130703 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6280. Min Act: -0.0000

Data Index: 862744 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1262992 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6394. Min Act: -0.0000

Data Index: 793834 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6242. Min Act: -0.0000

Data Index: 494640 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6662. Min Act: -0.0000

Data Index: 616068 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6417. Min Act: -0.0000

Data Index: 149134 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6121. Min Act: -0.0000

Data Index: 612821 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1215369 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.6053. Min Act: -0.0000

Data Index: 815375 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1250226 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1058681 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1267599 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.5848. Min Act: -0.0000

Data Index: 507145 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.0542. Min Range: -1.0542

Max Act: 0.5723. Min Act: -0.0000

Data Index: 264731 (C4 (Web Text))

Max Activating Token Index: 194