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

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

Neuron 4586 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: 1.1239. Min Range: -1.1239

Max Act: 1.1239. Min Act: -0.0000

Data Index: 1567255 (Python Code)

Max Activating Token Index: 272

Text #1

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6896. Min Act: -0.0000

Data Index: 1521022 (Python Code)

Max Activating Token Index: 235

Text #2

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1577411 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1523970 (Python Code)

Max Activating Token Index: 357

Text #4

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1521063 (Python Code)

Max Activating Token Index: 368

Text #5

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1641699 (Python Code)

Max Activating Token Index: 224

Text #6

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1637176 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6685. Min Act: -0.0000

Data Index: 1447539 (Python Code)

Max Activating Token Index: 611

Text #8

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1466567 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1527132 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1367195 (Python Code)

Max Activating Token Index: 941

Text #11

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1614993 (Python Code)

Max Activating Token Index: 923

Text #12

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.5798. Min Act: -0.0000

Data Index: 1592797 (Python Code)

Max Activating Token Index: 323

Text #13

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1486418 (Python Code)

Max Activating Token Index: 784

Text #14

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1486360 (Python Code)

Max Activating Token Index: 377

Text #15

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1637952 (Python Code)

Max Activating Token Index: 883

Text #16

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1386126 (Python Code)

Max Activating Token Index: 463

Text #17

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1403431 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1384131 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1632816 (Python Code)

Max Activating Token Index: 626