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

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

Neuron 3940 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.8694. Min Act: -0.0000

Data Index: 1441979 (Python Code)

Max Activating Token Index: 1011

Text #1

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.5672. Min Act: -0.0000

Data Index: 1596821 (Python Code)

Max Activating Token Index: 463

Text #2

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1637916 (Python Code)

Max Activating Token Index: 899

Text #3

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.6345. Min Act: -0.0000

Data Index: 1501478 (Python Code)

Max Activating Token Index: 369

Text #4

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.4416. Min Act: -0.0000

Data Index: 784960 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.2872. Min Act: -0.0000

Data Index: 1273969 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.3615. Min Act: -0.0000

Data Index: 495369 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.3021. Min Act: -0.0000

Data Index: 1649663 (Python Code)

Max Activating Token Index: 243

Text #8

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.3331. Min Act: -0.0000

Data Index: 151763 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.1842. Min Act: -0.0000

Data Index: 1196905 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1365460 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.3989. Min Act: -0.0000

Data Index: 383358 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.1838. Min Act: -0.0000

Data Index: 1533971 (Python Code)

Max Activating Token Index: 377

Text #13

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1576352 (Python Code)

Max Activating Token Index: 137

Text #14

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.2657. Min Act: -0.0000

Data Index: 488627 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.3210. Min Act: -0.0000

Data Index: 372621 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.1595. Min Act: -0.0000

Data Index: 191155 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1471807 (Python Code)

Max Activating Token Index: 466

Text #18

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1638312 (Python Code)

Max Activating Token Index: 505

Text #19

Max Range: 1.8694. Min Range: -1.8694

Max Act: 1.1511. Min Act: -0.0000

Data Index: 1641393 (Python Code)

Max Activating Token Index: 870