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

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

Neuron 5079 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.6248. Min Act: -0.0000

Data Index: 1534769 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1492663 (Python Code)

Max Activating Token Index: 141

Text #2

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5845. Min Act: -0.0000

Data Index: 14400 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1633030 (Python Code)

Max Activating Token Index: 584

Text #4

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1619082 (Python Code)

Max Activating Token Index: 418

Text #5

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1563423 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5032. Min Act: -0.0000

Data Index: 289330 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1501188 (Python Code)

Max Activating Token Index: 475

Text #8

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1546794 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1627417 (Python Code)

Max Activating Token Index: 657

Text #10

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1609752 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1615604 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1605895 (Python Code)

Max Activating Token Index: 405

Text #13

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1437896 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1546753 (Python Code)

Max Activating Token Index: 1022

Text #15

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1370188 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1370729 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1386602 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1455223 (Python Code)

Max Activating Token Index: 761

Text #19

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1514785 (Python Code)

Max Activating Token Index: 639