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

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

Neuron 4530 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1578159 (Python Code)

Max Activating Token Index: 331

Text #1

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1577693 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1554388 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1469647 (Python Code)

Max Activating Token Index: 311

Text #4

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1614659 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1543593 (Python Code)

Max Activating Token Index: 477

Text #6

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1461882 (Python Code)

Max Activating Token Index: 641

Text #7

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1650494 (Python Code)

Max Activating Token Index: 129

Text #8

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1537571 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3766. Min Act: -0.0000

Data Index: 171181 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1642545 (Python Code)

Max Activating Token Index: 830

Text #11

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1448154 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1389799 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1590738 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1509298 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1590909 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1299052 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3244. Min Act: -0.0000

Data Index: 1527556 (Python Code)

Max Activating Token Index: 55

Text #18

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1648635 (Python Code)

Max Activating Token Index: 271

Text #19

Max Range: 0.5245. Min Range: -0.5245

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1364749 (Python Code)

Max Activating Token Index: 256