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

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

Neuron 3652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1365139 (Python Code)

Max Activating Token Index: 991

Text #1

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1478235 (Python Code)

Max Activating Token Index: 218

Text #2

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.2830. Min Act: -0.0000

Data Index: 1541007 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.3427. Min Act: -0.0000

Data Index: 1632959 (Python Code)

Max Activating Token Index: 440

Text #4

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.1947. Min Act: -0.0000

Data Index: 1413208 (Python Code)

Max Activating Token Index: 985

Text #5

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1498262 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.1977. Min Act: -0.0000

Data Index: 1642221 (Python Code)

Max Activating Token Index: 328

Text #7

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.2597. Min Act: -0.0000

Data Index: 1464654 (Python Code)

Max Activating Token Index: 977

Text #8

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1588141 (Python Code)

Max Activating Token Index: 728

Text #9

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.2209. Min Act: -0.0000

Data Index: 1578963 (Python Code)

Max Activating Token Index: 679

Text #10

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1624970 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.1014. Min Act: -0.0000

Data Index: 1481914 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1372621 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1418698 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 1.4477. Min Range: -1.4477

Max Act: 0.9988. Min Act: -0.0000

Data Index: 1636819 (Python Code)

Max Activating Token Index: 711

Text #15

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.0691. Min Act: -0.0000

Data Index: 1443912 (Python Code)

Max Activating Token Index: 368

Text #16

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.1013. Min Act: -0.0000

Data Index: 1611613 (Python Code)

Max Activating Token Index: 245

Text #17

Max Range: 1.4477. Min Range: -1.4477

Max Act: 0.9862. Min Act: -0.0000

Data Index: 1380982 (Python Code)

Max Activating Token Index: 1015

Text #18

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.0157. Min Act: -0.0000

Data Index: 1495951 (Python Code)

Max Activating Token Index: 1020

Text #19

Max Range: 1.4477. Min Range: -1.4477

Max Act: 1.0336. Min Act: -0.0000

Data Index: 1380572 (Python Code)

Max Activating Token Index: 976