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

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

Neuron 1085 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1640. Min Act: -0.0000

Data Index: 648449 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1186955 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1455. Min Act: -0.0000

Data Index: 68935 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1435. Min Act: -0.0000

Data Index: 508951 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1270. Min Act: -0.0000

Data Index: 726559 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1194. Min Act: -0.0000

Data Index: 622103 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1122. Min Act: -0.0000

Data Index: 705432 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0967. Min Act: -0.0000

Data Index: 419523 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1327649 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1008. Min Act: -0.0000

Data Index: 182957 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.1075. Min Act: -0.0000

Data Index: 864059 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0978. Min Act: -0.0000

Data Index: 61708 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0965. Min Act: -0.0000

Data Index: 261020 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0984. Min Act: -0.0000

Data Index: 275283 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0976. Min Act: -0.0000

Data Index: 224221 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0939. Min Act: -0.0000

Data Index: 622720 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0804. Min Act: -0.0000

Data Index: 1300306 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0929. Min Act: -0.0000

Data Index: 912861 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1298312 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.1640. Min Range: -0.1640

Max Act: 0.0920. Min Act: -0.0000

Data Index: 884753 (C4 (Web Text))

Max Activating Token Index: 869