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

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

Neuron 1256 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.4846. Min Act: -0.0000

Data Index: 272560 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.3355. Min Act: -0.0000

Data Index: 693574 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1632. Min Act: -0.0000

Data Index: 646611 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1680. Min Act: -0.0000

Data Index: 739764 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1138. Min Act: -0.0000

Data Index: 609393 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1429. Min Act: -0.0000

Data Index: 106886 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.0729. Min Act: -0.0000

Data Index: 1187421 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.1231. Min Act: -0.0000

Data Index: 610752 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.0045. Min Act: -0.0000

Data Index: 883693 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1319628 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1048741 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1574821 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.8974. Min Act: -0.0000

Data Index: 992753 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.9851. Min Act: -0.0000

Data Index: 1347959 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.9171. Min Act: -0.0000

Data Index: 583822 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1105774 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.4846. Min Range: -1.4846

Max Act: 1.0043. Min Act: -0.0000

Data Index: 813935 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1300997 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.8286. Min Act: -0.0000

Data Index: 759307 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.4846. Min Range: -1.4846

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1327379 (C4 (Web Text))

Max Activating Token Index: 431