Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2562 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.4295. Min Act: -0.0002

Data Index: 1625721 (Python Code)

Max Activating Token Index: 35

Text #1

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.4232. Min Act: -0.0002

Data Index: 1513052 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.4071. Min Act: -0.0002

Data Index: 1644958 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.4256. Min Act: -0.0002

Data Index: 1407230 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3724. Min Act: -0.0002

Data Index: 1578626 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3736. Min Act: -0.0002

Data Index: 1622815 (Python Code)

Max Activating Token Index: 138

Text #6

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3723. Min Act: -0.0002

Data Index: 1558325 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3887. Min Act: -0.0002

Data Index: 1566878 (Python Code)

Max Activating Token Index: 123

Text #8

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3672. Min Act: -0.0002

Data Index: 1463730 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3516. Min Act: -0.0002

Data Index: 1474430 (Python Code)

Max Activating Token Index: 202

Text #10

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3387. Min Act: -0.0002

Data Index: 1397409 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3683. Min Act: -0.0002

Data Index: 1643705 (Python Code)

Max Activating Token Index: 807

Text #12

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3300. Min Act: -0.0002

Data Index: 1534969 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3430. Min Act: -0.0002

Data Index: 1533912 (Python Code)

Max Activating Token Index: 337

Text #14

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3382. Min Act: -0.0002

Data Index: 1568740 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3251. Min Act: -0.0002

Data Index: 1650859 (Python Code)

Max Activating Token Index: 798

Text #16

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3034. Min Act: -0.0002

Data Index: 1362347 (Python Code)

Max Activating Token Index: 618

Text #17

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3163. Min Act: -0.0002

Data Index: 1542468 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3476. Min Act: -0.0002

Data Index: 1458652 (Python Code)

Max Activating Token Index: 587

Text #19

Max Range: 0.4295. Min Range: -0.4295

Max Act: 0.3115. Min Act: -0.0002

Data Index: 1520097 (Python Code)

Max Activating Token Index: 333