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

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

Neuron 709 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: 2.1824. Min Range: -2.1824

Max Act: 2.1824. Min Act: -0.0000

Data Index: 1526811 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 2.1824. Min Range: -2.1824

Max Act: 2.0596. Min Act: -0.0000

Data Index: 264657 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.8767. Min Act: -0.0000

Data Index: 1363806 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.8857. Min Act: -0.0000

Data Index: 1566761 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1158059 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.8190. Min Act: -0.0000

Data Index: 1424517 (Python Code)

Max Activating Token Index: 636

Text #6

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.7795. Min Act: -0.0000

Data Index: 1490810 (Python Code)

Max Activating Token Index: 399

Text #7

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.7660. Min Act: -0.0000

Data Index: 448053 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.7363. Min Act: -0.0000

Data Index: 1375097 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.7192. Min Act: -0.0000

Data Index: 1598506 (Python Code)

Max Activating Token Index: 207

Text #10

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.5726. Min Act: -0.0000

Data Index: 120358 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.7537. Min Act: -0.0000

Data Index: 1638293 (Python Code)

Max Activating Token Index: 985

Text #12

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1591820 (Python Code)

Max Activating Token Index: 621

Text #13

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.6084. Min Act: -0.0000

Data Index: 1465153 (Python Code)

Max Activating Token Index: 663

Text #14

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.5926. Min Act: -0.0000

Data Index: 1185057 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.6317. Min Act: -0.0000

Data Index: 1475685 (Python Code)

Max Activating Token Index: 549

Text #16

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.4731. Min Act: -0.0000

Data Index: 588129 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.5711. Min Act: -0.0000

Data Index: 498267 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.5563. Min Act: -0.0000

Data Index: 1649359 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 2.1824. Min Range: -2.1824

Max Act: 1.5544. Min Act: -0.0000

Data Index: 1587199 (Python Code)

Max Activating Token Index: 133