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

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

Neuron 3064 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1379015 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1553011 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1526660 (Python Code)

Max Activating Token Index: 610

Text #3

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1620465 (Python Code)

Max Activating Token Index: 289

Text #4

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1492528 (Python Code)

Max Activating Token Index: 513

Text #5

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1365180 (Python Code)

Max Activating Token Index: 792

Text #6

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1657024 (Python Code)

Max Activating Token Index: 999

Text #7

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1503414 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1655979 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6031. Min Act: -0.0001

Data Index: 1484642 (Python Code)

Max Activating Token Index: 717

Text #10

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6300. Min Act: -0.0000

Data Index: 1495853 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1501259 (Python Code)

Max Activating Token Index: 345

Text #12

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1389098 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1435879 (Python Code)

Max Activating Token Index: 1000

Text #14

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1460461 (Python Code)

Max Activating Token Index: 1008

Text #15

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.6001. Min Act: -0.0000

Data Index: 1543171 (Python Code)

Max Activating Token Index: 795

Text #16

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1490437 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1382710 (Python Code)

Max Activating Token Index: 576

Text #18

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1444099 (Python Code)

Max Activating Token Index: 338

Text #19

Max Range: 0.8506. Min Range: -0.8506

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1474322 (Python Code)

Max Activating Token Index: 714