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

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

Neuron 6103 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.3184. Min Act: -0.0000

Data Index: 419569 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2878. Min Act: -0.0000

Data Index: 1588934 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.3016. Min Act: -0.0000

Data Index: 466893 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1574720 (Python Code)

Max Activating Token Index: 966

Text #4

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1566489 (Python Code)

Max Activating Token Index: 586

Text #5

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1412793 (Python Code)

Max Activating Token Index: 412

Text #6

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1471374 (Python Code)

Max Activating Token Index: 227

Text #7

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2758. Min Act: -0.0000

Data Index: 186736 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2555. Min Act: -0.0000

Data Index: 1513879 (Python Code)

Max Activating Token Index: 614

Text #9

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2626. Min Act: -0.0000

Data Index: 1397743 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1084148 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1569418 (Python Code)

Max Activating Token Index: 763

Text #12

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1147326 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1511432 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2420. Min Act: -0.0000

Data Index: 749788 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1614492 (Python Code)

Max Activating Token Index: 343

Text #16

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1411410 (Python Code)

Max Activating Token Index: 401

Text #17

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2591. Min Act: -0.0000

Data Index: 918548 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1502586 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 0.3184. Min Range: -0.3184

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1583506 (Python Code)

Max Activating Token Index: 148