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

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

Neuron 3919 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1016. Min Act: -0.0002

Data Index: 752790 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1069. Min Act: -0.0002

Data Index: 587278 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0002

Data Index: 167993 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1013. Min Act: -0.0002

Data Index: 926113 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1004. Min Act: -0.0002

Data Index: 130724 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1030. Min Act: -0.0002

Data Index: 436989 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1558226 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0909. Min Act: -0.0002

Data Index: 913841 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1376059 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0935. Min Act: -0.0002

Data Index: 937854 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0892. Min Act: -0.0002

Data Index: 600530 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0939. Min Act: -0.0002

Data Index: 776307 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0925. Min Act: -0.0002

Data Index: 52770 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0935. Min Act: -0.0001

Data Index: 621969 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0965. Min Act: -0.0002

Data Index: 700662 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0870. Min Act: -0.0002

Data Index: 647604 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1088156 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1445315 (Python Code)

Max Activating Token Index: 196

Text #18

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1565921 (Python Code)

Max Activating Token Index: 347

Text #19

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0882. Min Act: -0.0002

Data Index: 668045 (C4 (Web Text))

Max Activating Token Index: 110