Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3503 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.4155. Min Act: -0.0000

Data Index: 754846 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.2213. Min Act: -0.0000

Data Index: 1215859 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.3424. Min Act: -0.0001

Data Index: 269097 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.3266. Min Act: -0.0000

Data Index: 392484 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.1788. Min Act: -0.0001

Data Index: 421524 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.3044. Min Act: -0.0000

Data Index: 624862 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.2997. Min Act: -0.0001

Data Index: 881766 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.2923. Min Act: -0.0000

Data Index: 906397 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.2842. Min Act: -0.0001

Data Index: 478490 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.2692. Min Act: -0.0000

Data Index: 979014 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.1386. Min Act: -0.0000

Data Index: 121230 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.1222. Min Act: -0.0000

Data Index: 689818 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.1001. Min Act: -0.0001

Data Index: 867284 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.1950. Min Act: -0.0000

Data Index: 141165 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.2053. Min Act: -0.0000

Data Index: 58558 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.0825. Min Act: -0.0000

Data Index: 1055179 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.1825. Min Act: -0.0000

Data Index: 615518 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.1042. Min Act: -0.0000

Data Index: 209608 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.1888. Min Act: -0.0001

Data Index: 325863 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 2.4155. Min Range: -2.4155

Max Act: 2.1879. Min Act: -0.0000

Data Index: 906629 (C4 (Web Text))

Max Activating Token Index: 134