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

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

Neuron 561 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: 2.5200. Min Range: -2.5200

Max Act: 2.5200. Min Act: -0.0000

Data Index: 770988 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.4669. Min Act: -0.0000

Data Index: 1195826 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.3220. Min Act: -0.0000

Data Index: 74746 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.3156. Min Act: -0.0000

Data Index: 1284518 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.2764. Min Act: -0.0000

Data Index: 7485 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.3969. Min Act: -0.0000

Data Index: 453672 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.2767. Min Act: -0.0000

Data Index: 1292035 (C4 (Web Text))

Max Activating Token Index: 159

Text #7

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.2290. Min Act: -0.0000

Data Index: 399031 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.2002. Min Act: -0.0000

Data Index: 694441 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 2.5200. Min Range: -2.5200

Max Act: 1.9559. Min Act: -0.0000

Data Index: 945451 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.0391. Min Act: -0.0000

Data Index: 1023907 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.2423. Min Act: -0.0000

Data Index: 1044242 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.0921. Min Act: -0.0000

Data Index: 786332 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.2272. Min Act: -0.0000

Data Index: 1029311 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.0878. Min Act: -0.0000

Data Index: 1312570 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 2.5200. Min Range: -2.5200

Max Act: 1.9698. Min Act: -0.0000

Data Index: 398495 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.1789. Min Act: -0.0000

Data Index: 1149831 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.0472. Min Act: -0.0000

Data Index: 18891 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 2.5200. Min Range: -2.5200

Max Act: 1.8338. Min Act: -0.0000

Data Index: 1257897 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 2.5200. Min Range: -2.5200

Max Act: 2.0510. Min Act: -0.0000

Data Index: 666413 (C4 (Web Text))

Max Activating Token Index: 836