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

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

Neuron 1475 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: 2.4667. Min Range: -2.4667

Max Act: 2.3941. Min Act: -0.0000

Data Index: 538804 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 2.4667. Min Range: -2.4667

Max Act: 2.2712. Min Act: -0.0000

Data Index: 564657 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 2.4667. Min Range: -2.4667

Max Act: 2.4667. Min Act: -0.0000

Data Index: 1252424 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 2.4667. Min Range: -2.4667

Max Act: 2.1546. Min Act: -0.0001

Data Index: 104885 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.4667. Min Range: -2.4667

Max Act: 2.1428. Min Act: -0.0000

Data Index: 396429 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.9969. Min Act: -0.0000

Data Index: 1014430 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.9649. Min Act: -0.0000

Data Index: 297572 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.8807. Min Act: -0.0000

Data Index: 768544 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.8801. Min Act: -0.0000

Data Index: 1344038 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.8369. Min Act: -0.0001

Data Index: 918674 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.9304. Min Act: -0.0000

Data Index: 1021325 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.7993. Min Act: -0.0000

Data Index: 336491 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.5707. Min Act: -0.0001

Data Index: 479750 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.6615. Min Act: -0.0000

Data Index: 1103642 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.6499. Min Act: -0.0000

Data Index: 1510343 (Python Code)

Max Activating Token Index: 692

Text #15

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.6255. Min Act: -0.0000

Data Index: 317092 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.6134. Min Act: -0.0000

Data Index: 1350795 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.4787. Min Act: -0.0001

Data Index: 432820 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.4736. Min Act: -0.0000

Data Index: 209597 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 2.4667. Min Range: -2.4667

Max Act: 1.4677. Min Act: -0.0000

Data Index: 620468 (C4 (Web Text))

Max Activating Token Index: 801