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

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

Neuron 1227 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.7480. Min Act: -0.0000

Data Index: 1623462 (Python Code)

Max Activating Token Index: 275

Text #1

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.6277. Min Act: -0.0000

Data Index: 1391920 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.5623. Min Act: -0.0000

Data Index: 1384523 (Python Code)

Max Activating Token Index: 410

Text #3

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.5439. Min Act: -0.0000

Data Index: 1575631 (Python Code)

Max Activating Token Index: 531

Text #4

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.6732. Min Act: -0.0000

Data Index: 1514014 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.5229. Min Act: -0.0000

Data Index: 1465385 (Python Code)

Max Activating Token Index: 653

Text #6

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.7218. Min Act: -0.0000

Data Index: 1586665 (Python Code)

Max Activating Token Index: 206

Text #7

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.7421. Min Act: -0.0000

Data Index: 1601025 (Python Code)

Max Activating Token Index: 131

Text #8

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.4092. Min Act: -0.0000

Data Index: 1568008 (Python Code)

Max Activating Token Index: 634

Text #9

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.2662. Min Act: -0.0000

Data Index: 1387215 (Python Code)

Max Activating Token Index: 935

Text #10

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.4927. Min Act: -0.0000

Data Index: 1534025 (Python Code)

Max Activating Token Index: 254

Text #11

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.5000. Min Act: -0.0000

Data Index: 1366915 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.4951. Min Act: -0.0000

Data Index: 1582697 (Python Code)

Max Activating Token Index: 699

Text #13

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.3488. Min Act: -0.0000

Data Index: 1444962 (Python Code)

Max Activating Token Index: 348

Text #14

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.6205. Min Act: -0.0000

Data Index: 1392435 (Python Code)

Max Activating Token Index: 84

Text #15

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.4663. Min Act: -0.0000

Data Index: 1620790 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.4404. Min Act: -0.0000

Data Index: 1396100 (Python Code)

Max Activating Token Index: 813

Text #17

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.4349. Min Act: -0.0000

Data Index: 1639818 (Python Code)

Max Activating Token Index: 608

Text #18

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.4243. Min Act: -0.0000

Data Index: 1620887 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 2.7480. Min Range: -2.7480

Max Act: 2.4117. Min Act: -0.0000

Data Index: 1415557 (Python Code)

Max Activating Token Index: 945