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

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

Neuron 4785 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0530. Min Act: -0.0002

Data Index: 210807 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0002

Data Index: 246591 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1327132 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1336064 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0454. Min Act: -0.0002

Data Index: 223538 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1050529 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0446. Min Act: -0.0002

Data Index: 173365 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0408. Min Act: -0.0002

Data Index: 292717 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1147804 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0429. Min Act: -0.0002

Data Index: 570740 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0422. Min Act: -0.0002

Data Index: 199101 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0394. Min Act: -0.0002

Data Index: 723394 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0395. Min Act: -0.0002

Data Index: 634991 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0408. Min Act: -0.0002

Data Index: 49578 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1252087 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0404. Min Act: -0.0002

Data Index: 40905 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1062238 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1076252 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0388. Min Act: -0.0002

Data Index: 319697 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0390. Min Act: -0.0002

Data Index: 738814 (C4 (Web Text))

Max Activating Token Index: 248