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

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

Neuron 4439 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.4992. Min Act: -0.0000

Data Index: 1501325 (Python Code)

Max Activating Token Index: 174

Text #1

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.3313. Min Act: -0.0000

Data Index: 855460 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.1193. Min Act: -0.0000

Data Index: 1232889 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.0487. Min Act: -0.0000

Data Index: 1215076 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.0685. Min Act: -0.0000

Data Index: 93297 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.9748. Min Act: -0.0000

Data Index: 409710 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.0436. Min Act: -0.0000

Data Index: 548849 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.0589. Min Act: -0.0000

Data Index: 775807 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.9460. Min Act: -0.0000

Data Index: 1001055 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.0005. Min Act: -0.0000

Data Index: 623845 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.8473. Min Act: -0.0000

Data Index: 501682 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1154956 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.9697. Min Act: -0.0000

Data Index: 878125 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1198758 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.8884. Min Act: -0.0000

Data Index: 328866 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.4992. Min Range: -1.4992

Max Act: 1.0222. Min Act: -0.0000

Data Index: 584401 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1381780 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1344641 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.8744. Min Act: -0.0000

Data Index: 188630 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.4992. Min Range: -1.4992

Max Act: 0.8416. Min Act: -0.0000

Data Index: 44393 (C4 (Web Text))

Max Activating Token Index: 642