Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2268 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1270373 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1110. Min Act: -0.0000

Data Index: 665927 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1293467 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1351327 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0934. Min Act: -0.0000

Data Index: 818134 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0959. Min Act: -0.0000

Data Index: 349925 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0923. Min Act: -0.0001

Data Index: 719107 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0928. Min Act: -0.0000

Data Index: 278003 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0896. Min Act: -0.0001

Data Index: 680362 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0882. Min Act: -0.0000

Data Index: 666580 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0876. Min Act: -0.0000

Data Index: 833899 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0862. Min Act: -0.0001

Data Index: 718558 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0860. Min Act: -0.0001

Data Index: 853277 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0860. Min Act: -0.0000

Data Index: 824767 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0852. Min Act: -0.0000

Data Index: 537574 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0834. Min Act: -0.0001

Data Index: 374619 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0833. Min Act: -0.0000

Data Index: 507951 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0829. Min Act: -0.0001

Data Index: 254742 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0801. Min Act: -0.0000

Data Index: 79950 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0841. Min Act: -0.0000

Data Index: 171221 (C4 (Web Text))

Max Activating Token Index: 506