Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2024 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3879. Min Range: -2.3879

Max Act: 2.3879. Min Act: -0.0000

Data Index: 1216088 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.7136. Min Act: -0.0000

Data Index: 804129 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.7640. Min Act: -0.0000

Data Index: 1331553 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1246230 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.3596. Min Act: -0.0000

Data Index: 411449 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.2779. Min Act: -0.0000

Data Index: 449822 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.2094. Min Act: -0.0000

Data Index: 101522 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.1193. Min Act: -0.0000

Data Index: 451744 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.2568. Min Act: -0.0000

Data Index: 834726 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.1741. Min Act: -0.0000

Data Index: 387369 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1087351 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.1310. Min Act: -0.0000

Data Index: 556435 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.0473. Min Act: -0.0000

Data Index: 614562 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1338881 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.0850. Min Act: -0.0000

Data Index: 340026 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.0799. Min Act: -0.0000

Data Index: 870679 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.0116. Min Act: -0.0000

Data Index: 1091372 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1278430 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.0645. Min Act: -0.0000

Data Index: 805792 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 2.3879. Min Range: -2.3879

Max Act: 1.1269. Min Act: -0.0000

Data Index: 498198 (C4 (Web Text))

Max Activating Token Index: 385