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

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

Neuron 5369 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5923. Min Range: -2.5923

Max Act: 2.5923. Min Act: -0.0000

Data Index: 162746 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 2.5923. Min Range: -2.5923

Max Act: 2.2615. Min Act: -0.0000

Data Index: 610638 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 2.5923. Min Range: -2.5923

Max Act: 2.4149. Min Act: -0.0000

Data Index: 352251 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 2.5923. Min Range: -2.5923

Max Act: 2.1566. Min Act: -0.0000

Data Index: 665766 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 2.5923. Min Range: -2.5923

Max Act: 2.1423. Min Act: -0.0000

Data Index: 792960 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 2.5923. Min Range: -2.5923

Max Act: 2.1311. Min Act: -0.0000

Data Index: 986708 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 2.5923. Min Range: -2.5923

Max Act: 2.1894. Min Act: -0.0000

Data Index: 768146 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.9501. Min Act: -0.0000

Data Index: 1086512 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 2.5923. Min Range: -2.5923

Max Act: 2.0473. Min Act: -0.0000

Data Index: 335504 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.8794. Min Act: -0.0000

Data Index: 465020 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.7834. Min Act: -0.0000

Data Index: 263499 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.8853. Min Act: -0.0000

Data Index: 1097940 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.8552. Min Act: -0.0000

Data Index: 451165 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.8317. Min Act: -0.0000

Data Index: 255640 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.9279. Min Act: -0.0000

Data Index: 792299 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.9035. Min Act: -0.0000

Data Index: 1012378 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.6985. Min Act: -0.0000

Data Index: 485747 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.7763. Min Act: -0.0000

Data Index: 1197834 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.7706. Min Act: -0.0000

Data Index: 450260 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 2.5923. Min Range: -2.5923

Max Act: 1.5638. Min Act: -0.0000

Data Index: 160559 (C4 (Web Text))

Max Activating Token Index: 726