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

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

Neuron 3455 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: 2.4218. Min Range: -2.4218

Max Act: 2.4218. Min Act: -0.0000

Data Index: 1076221 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.6776. Min Act: -0.0000

Data Index: 1357615 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1009737 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.3017. Min Act: -0.0000

Data Index: 1104149 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.3197. Min Act: -0.0000

Data Index: 350838 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.3146. Min Act: -0.0000

Data Index: 904403 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.3350. Min Act: -0.0000

Data Index: 610536 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.2878. Min Act: -0.0000

Data Index: 79716 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.0825. Min Act: -0.0000

Data Index: 824736 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.2833. Min Act: -0.0000

Data Index: 828052 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1266869 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.1762. Min Act: -0.0000

Data Index: 1370614 (Python Code)

Max Activating Token Index: 757

Text #12

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.1035. Min Act: -0.0000

Data Index: 893954 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.2020. Min Act: -0.0000

Data Index: 372801 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.0706. Min Act: -0.0000

Data Index: 333937 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.1841. Min Act: -0.0000

Data Index: 951678 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1526646 (Python Code)

Max Activating Token Index: 937

Text #17

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.1635. Min Act: -0.0000

Data Index: 66286 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 2.4218. Min Range: -2.4218

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1513110 (Python Code)

Max Activating Token Index: 896

Text #19

Max Range: 2.4218. Min Range: -2.4218

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1590436 (Python Code)

Max Activating Token Index: 712