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

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

Neuron 1520 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1063300 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.5528. Min Act: -0.0000

Data Index: 1332340 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.5486. Min Act: -0.0000

Data Index: 112848 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.5499. Min Act: -0.0000

Data Index: 525330 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1041899 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.4807. Min Act: -0.0000

Data Index: 69436 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.4750. Min Act: -0.0000

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1038682 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.3346. Min Act: -0.0000

Data Index: 220475 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2970. Min Act: -0.0000

Data Index: 701729 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2834. Min Act: -0.0000

Data Index: 755022 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2522. Min Act: -0.0000

Data Index: 370431 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2896. Min Act: -0.0000

Data Index: 425678 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2494. Min Act: -0.0000

Data Index: 1390784 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2793. Min Act: -0.0000

Data Index: 646739 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1603081 (Python Code)

Max Activating Token Index: 834

Text #16

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2368. Min Act: -0.0000

Data Index: 752154 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1397334 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1175539 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.6126. Min Range: -0.6126

Max Act: 0.2251. Min Act: -0.0000

Data Index: 936322 (C4 (Web Text))

Max Activating Token Index: 84