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

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

Neuron 2115 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7725. Min Range: -6.7725

Max Act: 6.5908. Min Act: -0.0001

Data Index: 1012607 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 6.7725. Min Range: -6.7725

Max Act: 6.2042. Min Act: -0.0000

Data Index: 778665 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 6.7725. Min Range: -6.7725

Max Act: 6.2617. Min Act: -0.0001

Data Index: 1236761 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 6.7725. Min Range: -6.7725

Max Act: 6.7653. Min Act: -0.0001

Data Index: 1095771 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 6.7725. Min Range: -6.7725

Max Act: 6.6032. Min Act: -0.0000

Data Index: 647961 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 6.7725. Min Range: -6.7725

Max Act: 6.2248. Min Act: -0.0001

Data Index: 697048 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 6.7725. Min Range: -6.7725

Max Act: 6.7725. Min Act: -0.0001

Data Index: 159597 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 6.7725. Min Range: -6.7725

Max Act: 5.4829. Min Act: -0.0001

Data Index: 308856 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 6.7725. Min Range: -6.7725

Max Act: 4.9429. Min Act: -0.0001

Data Index: 229484 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 6.7725. Min Range: -6.7725

Max Act: 6.0760. Min Act: -0.0001

Data Index: 234088 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 6.7725. Min Range: -6.7725

Max Act: 5.4684. Min Act: -0.0000

Data Index: 1250122 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 6.7725. Min Range: -6.7725

Max Act: 3.9194. Min Act: -0.0000

Data Index: 787795 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 6.7725. Min Range: -6.7725

Max Act: 4.0429. Min Act: -0.0001

Data Index: 1235598 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 6.7725. Min Range: -6.7725

Max Act: 3.7887. Min Act: -0.0000

Data Index: 398038 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 6.7725. Min Range: -6.7725

Max Act: 3.3266. Min Act: -0.0000

Data Index: 515993 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 6.7725. Min Range: -6.7725

Max Act: 3.4684. Min Act: -0.0000

Data Index: 1279332 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 6.7725. Min Range: -6.7725

Max Act: 3.4508. Min Act: -0.0000

Data Index: 841512 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 6.7725. Min Range: -6.7725

Max Act: 3.1095. Min Act: -0.0001

Data Index: 399219 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 6.7725. Min Range: -6.7725

Max Act: 4.0150. Min Act: -0.0000

Data Index: 1026777 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 6.7725. Min Range: -6.7725

Max Act: 3.5046. Min Act: -0.0000

Data Index: 389063 (C4 (Web Text))

Max Activating Token Index: 52