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

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

Neuron 3321 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.4423. Min Act: -0.0002

Data Index: 98670 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.2068. Min Act: -0.0002

Data Index: 1193127 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.1981. Min Act: -0.0002

Data Index: 517125 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.1373. Min Act: -0.0002

Data Index: 1108494 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.1707. Min Act: -0.0002

Data Index: 136865 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.1182. Min Act: -0.0002

Data Index: 572484 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.1294. Min Act: -0.0002

Data Index: 1323861 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.1254. Min Act: -0.0002

Data Index: 1331047 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0959. Min Act: -0.0002

Data Index: 1076490 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0884. Min Act: -0.0002

Data Index: 334421 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0916. Min Act: -0.0002

Data Index: 618540 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0766. Min Act: -0.0002

Data Index: 253736 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0723. Min Act: -0.0002

Data Index: 702154 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0644. Min Act: -0.0002

Data Index: 988492 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0651. Min Act: -0.0002

Data Index: 719316 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0556. Min Act: -0.0002

Data Index: 845061 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0628. Min Act: -0.0002

Data Index: 314150 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0617. Min Act: -0.0002

Data Index: 890459 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0615. Min Act: -0.0002

Data Index: 1268928 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.4423. Min Range: -1.4423

Max Act: 1.0563. Min Act: -0.0002

Data Index: 207851 (C4 (Web Text))

Max Activating Token Index: 8