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

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

Neuron 2613 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.7913. Min Act: -0.0000

Data Index: 879473 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.6120. Min Act: -0.0000

Data Index: 4652 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.6030. Min Act: -0.0000

Data Index: 231649 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1031504 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5804. Min Act: -0.0000

Data Index: 977392 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5659. Min Act: -0.0000

Data Index: 529276 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.5207. Min Act: -0.0000

Data Index: 678489 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.6051. Min Act: -0.0000

Data Index: 335087 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1309767 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.4020. Min Act: -0.0000

Data Index: 471440 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.4746. Min Act: -0.0000

Data Index: 641199 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.3928. Min Act: -0.0000

Data Index: 605830 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.4458. Min Act: -0.0000

Data Index: 782010 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.4030. Min Act: -0.0000

Data Index: 208465 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.4012. Min Act: -0.0000

Data Index: 42346 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.3733. Min Act: -0.0000

Data Index: 121732 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.3904. Min Act: -0.0000

Data Index: 79401 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.3617. Min Act: -0.0000

Data Index: 84665 (C4 (Web Text))

Max Activating Token Index: 688

Text #18

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1125367 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.7913. Min Range: -0.7913

Max Act: 0.3681. Min Act: -0.0000

Data Index: 606680 (C4 (Web Text))

Max Activating Token Index: 419