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

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

Neuron 3505 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: 0.2788. Min Range: -0.2788

Max Act: 0.2788. Min Act: -0.0000

Data Index: 804992 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2335. Min Act: -0.0000

Data Index: 268061 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1351461 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1307549 (C4 (Web Text))

Max Activating Token Index: 475

Text #4

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2248. Min Act: -0.0000

Data Index: 216842 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2154. Min Act: -0.0000

Data Index: 324151 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1206535 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.2048. Min Act: -0.0000

Data Index: 408909 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1802. Min Act: -0.0000

Data Index: 348129 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1171253 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1794. Min Act: -0.0000

Data Index: 293161 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1732. Min Act: -0.0000

Data Index: 459062 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1666. Min Act: -0.0000

Data Index: 49500 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1553. Min Act: -0.0000

Data Index: 512048 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1495. Min Act: -0.0000

Data Index: 6188 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1506. Min Act: -0.0000

Data Index: 920435 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1482. Min Act: -0.0000

Data Index: 989866 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1338. Min Act: -0.0000

Data Index: 1025637 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1429. Min Act: -0.0000

Data Index: 852140 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.2788. Min Range: -0.2788

Max Act: 0.1347. Min Act: -0.0000

Data Index: 584469 (C4 (Web Text))

Max Activating Token Index: 822