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

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

Neuron 6030 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.6281. Min Act: -0.0000

Data Index: 9258 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.5866. Min Act: -0.0000

Data Index: 132188 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.7617. Min Act: -0.0000

Data Index: 628981 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.7156. Min Act: -0.0000

Data Index: 537407 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.6588. Min Act: -0.0000

Data Index: 434790 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.6459. Min Act: -0.0000

Data Index: 1199691 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.8062. Min Act: -0.0000

Data Index: 987697 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.5986. Min Act: -0.0000

Data Index: 964069 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.7919. Min Act: -0.0000

Data Index: 1248516 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.4063. Min Act: -0.0000

Data Index: 312544 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.5792. Min Act: -0.0000

Data Index: 183220 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.7610. Min Act: -0.0000

Data Index: 71958 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.7610. Min Act: -0.0000

Data Index: 1172566 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.5809. Min Act: -0.0000

Data Index: 1313811 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.3928. Min Act: -0.0000

Data Index: 338257 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.5673. Min Act: -0.0000

Data Index: 642338 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.5616. Min Act: -0.0000

Data Index: 917611 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.5620. Min Act: -0.0000

Data Index: 1216458 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.5560. Min Act: -0.0000

Data Index: 43503 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 4.8062. Min Range: -4.8062

Max Act: 4.5593. Min Act: -0.0000

Data Index: 717436 (C4 (Web Text))

Max Activating Token Index: 121