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

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

Neuron 4620 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1362283 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1597011 (Python Code)

Max Activating Token Index: 280

Text #2

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1364305 (Python Code)

Max Activating Token Index: 91

Text #3

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1555859 (Python Code)

Max Activating Token Index: 784

Text #4

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1586500 (Python Code)

Max Activating Token Index: 793

Text #5

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1387702 (Python Code)

Max Activating Token Index: 921

Text #6

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5137. Min Act: -0.0001

Data Index: 1650499 (Python Code)

Max Activating Token Index: 294

Text #7

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1440801 (Python Code)

Max Activating Token Index: 977

Text #8

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1513434 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1426211 (Python Code)

Max Activating Token Index: 440

Text #10

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1372666 (Python Code)

Max Activating Token Index: 971

Text #11

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1458026 (Python Code)

Max Activating Token Index: 234

Text #12

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1518424 (Python Code)

Max Activating Token Index: 529

Text #13

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1418012 (Python Code)

Max Activating Token Index: 877

Text #14

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1446086 (Python Code)

Max Activating Token Index: 198

Text #15

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1495108 (Python Code)

Max Activating Token Index: 251

Text #16

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1389816 (Python Code)

Max Activating Token Index: 809

Text #17

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4611. Min Act: -0.0000

Data Index: 1527822 (Python Code)

Max Activating Token Index: 854

Text #18

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1468084 (Python Code)

Max Activating Token Index: 911

Text #19

Max Range: 0.5437. Min Range: -0.5437

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1593568 (Python Code)

Max Activating Token Index: 804