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

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

Neuron 2057 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.5850. Min Act: -0.0000

Data Index: 167574 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4952. Min Act: -0.0000

Data Index: 763867 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4209. Min Act: -0.0000

Data Index: 192343 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4460. Min Act: -0.0000

Data Index: 301668 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4147. Min Act: -0.0000

Data Index: 726789 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3765. Min Act: -0.0000

Data Index: 1054463 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4266. Min Act: -0.0000

Data Index: 621107 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.4015. Min Act: -0.0000

Data Index: 923704 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3999. Min Act: -0.0000

Data Index: 826380 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3815. Min Act: -0.0000

Data Index: 386079 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1289127 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3522. Min Act: -0.0000

Data Index: 259774 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3353. Min Act: -0.0000

Data Index: 490789 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3357. Min Act: -0.0000

Data Index: 493425 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3565. Min Act: -0.0000

Data Index: 952922 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3287. Min Act: -0.0000

Data Index: 770407 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3466. Min Act: -0.0000

Data Index: 677476 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3436. Min Act: -0.0000

Data Index: 304542 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3442. Min Act: -0.0000

Data Index: 907111 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.5850. Min Range: -0.5850

Max Act: 0.3342. Min Act: -0.0000

Data Index: 560824 (C4 (Web Text))

Max Activating Token Index: 257