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

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

Neuron 4135 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1134471 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1349524 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0791. Min Act: -0.0001

Data Index: 229677 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0839. Min Act: -0.0001

Data Index: 453585 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0848. Min Act: -0.0001

Data Index: 1098244 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1257630 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1060541 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0744. Min Act: -0.0001

Data Index: 2501 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0738. Min Act: -0.0001

Data Index: 762487 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0685. Min Act: -0.0001

Data Index: 669833 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0708. Min Act: -0.0001

Data Index: 897191 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0697. Min Act: -0.0001

Data Index: 234164 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1175759 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1180084 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0717. Min Act: -0.0001

Data Index: 661996 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0689. Min Act: -0.0001

Data Index: 891086 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0702. Min Act: -0.0001

Data Index: 238613 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0666. Min Act: -0.0001

Data Index: 831135 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0599. Min Act: -0.0001

Data Index: 805443 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.0856. Min Range: -0.0856

Max Act: 0.0621. Min Act: -0.0001

Data Index: 1096750 (C4 (Web Text))

Max Activating Token Index: 190