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

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

Neuron 4614 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: 1.9038. Min Range: -1.9038

Max Act: 1.9038. Min Act: -0.0000

Data Index: 359753 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.8909. Min Act: -0.0000

Data Index: 612762 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.6485. Min Act: -0.0000

Data Index: 494773 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.6632. Min Act: -0.0000

Data Index: 705346 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.5952. Min Act: -0.0000

Data Index: 770692 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.6445. Min Act: -0.0000

Data Index: 956773 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.2870. Min Act: -0.0000

Data Index: 880213 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.5250. Min Act: -0.0000

Data Index: 891884 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.7256. Min Act: -0.0000

Data Index: 26530 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.4215. Min Act: -0.0000

Data Index: 1033663 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.5024. Min Act: -0.0000

Data Index: 1303923 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.4532. Min Act: -0.0000

Data Index: 1176553 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.4031. Min Act: -0.0000

Data Index: 859662 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.3378. Min Act: -0.0000

Data Index: 606873 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.1620. Min Act: -0.0000

Data Index: 1164917 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.2838. Min Act: -0.0000

Data Index: 618054 (C4 (Web Text))

Max Activating Token Index: 598

Text #16

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.4481. Min Act: -0.0000

Data Index: 181522 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.2488. Min Act: -0.0000

Data Index: 315556 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.2904. Min Act: -0.0000

Data Index: 273247 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.9038. Min Range: -1.9038

Max Act: 1.1492. Min Act: -0.0000

Data Index: 872814 (C4 (Web Text))

Max Activating Token Index: 608