Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1768 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: -0.0006

Data Index: 1341531 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0428. Min Act: -0.0006

Data Index: 1016020 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0417. Min Act: -0.0006

Data Index: 1345296 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0409. Min Act: -0.0006

Data Index: 1168620 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0394. Min Act: -0.0005

Data Index: 18970 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0394. Min Act: -0.0006

Data Index: 611121 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0399. Min Act: -0.0006

Data Index: 222664 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0376. Min Act: -0.0005

Data Index: 1276846 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0387. Min Act: -0.0006

Data Index: 1118078 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0386. Min Act: -0.0006

Data Index: 131564 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0378. Min Act: -0.0005

Data Index: 1443479 (Python Code)

Max Activating Token Index: 627

Text #11

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0387. Min Act: -0.0006

Data Index: 790147 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0377. Min Act: -0.0006

Data Index: 1044096 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0363. Min Act: -0.0005

Data Index: 28938 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0379. Min Act: -0.0006

Data Index: 907182 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0369. Min Act: -0.0006

Data Index: 109218 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0369. Min Act: -0.0006

Data Index: 197859 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0376. Min Act: -0.0006

Data Index: 776143 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0372. Min Act: -0.0006

Data Index: 296430 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0370. Min Act: -0.0006

Data Index: 139453 (C4 (Web Text))

Max Activating Token Index: 629