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

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

Neuron 3409 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.8090. Min Act: -0.0002

Data Index: 235370 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5854. Min Act: -0.0002

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5637. Min Act: -0.0003

Data Index: 1899 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5984. Min Act: -0.0002

Data Index: 1207583 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5945. Min Act: -0.0002

Data Index: 164986 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5937. Min Act: -0.0003

Data Index: 1024826 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5485. Min Act: -0.0003

Data Index: 376839 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5646. Min Act: -0.0003

Data Index: 963694 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.4507. Min Act: -0.0003

Data Index: 156057 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.4960. Min Act: -0.0002

Data Index: 274732 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5528. Min Act: -0.0002

Data Index: 1358322 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5294. Min Act: -0.0003

Data Index: 128323 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.4936. Min Act: -0.0003

Data Index: 478115 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.4904. Min Act: -0.0003

Data Index: 396191 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.5130. Min Act: -0.0002

Data Index: 962784 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.4606. Min Act: -0.0003

Data Index: 565084 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.4892. Min Act: -0.0003

Data Index: 991912 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.4999. Min Act: -0.0003

Data Index: 864680 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.4557. Min Act: -0.0003

Data Index: 118656 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.8090. Min Range: -0.8090

Max Act: 0.4353. Min Act: -0.0003

Data Index: 1083768 (C4 (Web Text))

Max Activating Token Index: 834