Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2046 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0986. Min Act: -0.0003

Data Index: 726762 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0975. Min Act: -0.0003

Data Index: 683105 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0928. Min Act: -0.0004

Data Index: 54893 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0868. Min Act: -0.0003

Data Index: 20356 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0903. Min Act: -0.0003

Data Index: 211423 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0853. Min Act: -0.0003

Data Index: 1312308 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0880. Min Act: -0.0003

Data Index: 1335702 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0864. Min Act: -0.0003

Data Index: 895816 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0871. Min Act: -0.0003

Data Index: 1277315 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0878. Min Act: -0.0003

Data Index: 1051396 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0857. Min Act: -0.0004

Data Index: 222150 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0836. Min Act: -0.0004

Data Index: 647423 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0851. Min Act: -0.0004

Data Index: 275565 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0828. Min Act: -0.0004

Data Index: 101556 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0834. Min Act: -0.0002

Data Index: 623098 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1164106 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0822. Min Act: -0.0003

Data Index: 1070684 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0812. Min Act: -0.0003

Data Index: 175659 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0802. Min Act: -0.0003

Data Index: 802983 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0845. Min Act: -0.0002

Data Index: 1284479 (C4 (Web Text))

Max Activating Token Index: 146