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

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

Neuron 514 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2795. Min Range: -1.2795

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1639673 (Python Code)

Max Activating Token Index: 622

Text #1

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.9846. Min Act: -0.0000

Data Index: 1362391 (Python Code)

Max Activating Token Index: 488

Text #2

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1500021 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1379200 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1639203 (Python Code)

Max Activating Token Index: 913

Text #5

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1540126 (Python Code)

Max Activating Token Index: 234

Text #6

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.7668. Min Act: -0.0000

Data Index: 1601275 (Python Code)

Max Activating Token Index: 979

Text #7

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.7344. Min Act: -0.0000

Data Index: 1656858 (Python Code)

Max Activating Token Index: 371

Text #8

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.7177. Min Act: -0.0000

Data Index: 1405948 (Python Code)

Max Activating Token Index: 90

Text #9

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1406127 (Python Code)

Max Activating Token Index: 955

Text #10

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.6915. Min Act: -0.0000

Data Index: 1604212 (Python Code)

Max Activating Token Index: 946

Text #11

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1492565 (Python Code)

Max Activating Token Index: 444

Text #12

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1601264 (Python Code)

Max Activating Token Index: 938

Text #13

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1610880 (Python Code)

Max Activating Token Index: 997

Text #14

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1385285 (Python Code)

Max Activating Token Index: 450

Text #15

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1628944 (Python Code)

Max Activating Token Index: 650

Text #16

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1377853 (Python Code)

Max Activating Token Index: 265

Text #17

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1476181 (Python Code)

Max Activating Token Index: 317

Text #18

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.6061. Min Act: -0.0000

Data Index: 1555871 (Python Code)

Max Activating Token Index: 635

Text #19

Max Range: 1.2795. Min Range: -1.2795

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1567435 (Python Code)

Max Activating Token Index: 582