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

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

Neuron 1364 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.8685. Min Act: -0.0000

Data Index: 1394650 (Python Code)

Max Activating Token Index: 219

Text #1

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.9539. Min Act: -0.0000

Data Index: 1490971 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.8208. Min Act: -0.0000

Data Index: 1508722 (Python Code)

Max Activating Token Index: 225

Text #3

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.6886. Min Act: -0.0000

Data Index: 1635442 (Python Code)

Max Activating Token Index: 380

Text #4

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.7489. Min Act: -0.0000

Data Index: 1510341 (Python Code)

Max Activating Token Index: 220

Text #5

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.5247. Min Act: -0.0000

Data Index: 1393566 (Python Code)

Max Activating Token Index: 93

Text #6

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.7052. Min Act: -0.0000

Data Index: 1603965 (Python Code)

Max Activating Token Index: 725

Text #7

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.4808. Min Act: -0.0000

Data Index: 1570048 (Python Code)

Max Activating Token Index: 253

Text #8

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.6078. Min Act: -0.0000

Data Index: 1608056 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.5155. Min Act: -0.0000

Data Index: 1649069 (Python Code)

Max Activating Token Index: 98

Text #10

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.5090. Min Act: -0.0000

Data Index: 1574524 (Python Code)

Max Activating Token Index: 710

Text #11

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.4939. Min Act: -0.0000

Data Index: 1449517 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.5564. Min Act: -0.0000

Data Index: 1510715 (Python Code)

Max Activating Token Index: 270

Text #13

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.4395. Min Act: -0.0000

Data Index: 1543715 (Python Code)

Max Activating Token Index: 656

Text #14

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.3284. Min Act: -0.0000

Data Index: 1590254 (Python Code)

Max Activating Token Index: 872

Text #15

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.2711. Min Act: -0.0000

Data Index: 1583222 (Python Code)

Max Activating Token Index: 897

Text #16

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.3769. Min Act: -0.0000

Data Index: 1511506 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1511836 (Python Code)

Max Activating Token Index: 476

Text #18

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1538805 (Python Code)

Max Activating Token Index: 655

Text #19

Max Range: 1.9539. Min Range: -1.9539

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1397019 (Python Code)

Max Activating Token Index: 213