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

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

Neuron 2992 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: 1.3439. Min Range: -1.3439

Max Act: 1.3439. Min Act: -0.0000

Data Index: 997074 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1311193 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1107940 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.8840. Min Act: -0.0000

Data Index: 620334 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1265398 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.8651. Min Act: -0.0000

Data Index: 74837 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1326025 (C4 (Web Text))

Max Activating Token Index: 757

Text #7

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1245023 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.8028. Min Act: -0.0000

Data Index: 225261 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.7995. Min Act: -0.0000

Data Index: 992915 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1321323 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.7667. Min Act: -0.0000

Data Index: 252763 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1646737 (Python Code)

Max Activating Token Index: 834

Text #13

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.8300. Min Act: -0.0000

Data Index: 382952 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.7954. Min Act: -0.0000

Data Index: 1214924 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1120273 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.7359. Min Act: -0.0000

Data Index: 78297 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.6980. Min Act: -0.0000

Data Index: 780297 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.7646. Min Act: -0.0000

Data Index: 347010 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 1.3439. Min Range: -1.3439

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1158848 (C4 (Web Text))

Max Activating Token Index: 136