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

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

Neuron 2817 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8773. Min Act: -0.0000

Data Index: 128659 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.8630. Min Act: -0.0000

Data Index: 114114 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7651. Min Act: -0.0000

Data Index: 533130 (C4 (Web Text))

Max Activating Token Index: 77

Text #3

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1345520 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6829. Min Act: -0.0000

Data Index: 296126 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1247798 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6931. Min Act: -0.0000

Data Index: 22592 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7072. Min Act: -0.0000

Data Index: 479137 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6796. Min Act: -0.0000

Data Index: 630458 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.7022. Min Act: -0.0000

Data Index: 736499 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6745. Min Act: -0.0000

Data Index: 265036 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6565. Min Act: -0.0000

Data Index: 984055 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.6040. Min Act: -0.0000

Data Index: 510640 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5750. Min Act: -0.0000

Data Index: 333876 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1091778 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5492. Min Act: -0.0000

Data Index: 306309 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5687. Min Act: -0.0000

Data Index: 954705 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1263415 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1337296 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.8773. Min Range: -0.8773

Max Act: 0.5590. Min Act: -0.0000

Data Index: 868718 (C4 (Web Text))

Max Activating Token Index: 326