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

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

Neuron 678 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: 0.8769. Min Range: -0.8769

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1332919 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.8765. Min Act: -0.0000

Data Index: 304833 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.8687. Min Act: -0.0000

Data Index: 416158 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.7422. Min Act: -0.0000

Data Index: 1194975 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.7459. Min Act: -0.0000

Data Index: 723982 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.7275. Min Act: -0.0000

Data Index: 278817 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6851. Min Act: -0.0000

Data Index: 1254678 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1132165 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6779. Min Act: -0.0000

Data Index: 889981 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1080235 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6770. Min Act: -0.0000

Data Index: 855544 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6387. Min Act: -0.0000

Data Index: 782538 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6713. Min Act: -0.0000

Data Index: 69310 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6519. Min Act: -0.0000

Data Index: 584155 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5831. Min Act: -0.0000

Data Index: 860428 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1053859 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6394. Min Act: -0.0000

Data Index: 391481 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6131. Min Act: -0.0000

Data Index: 592097 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.5718. Min Act: -0.0000

Data Index: 942259 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.8769. Min Range: -0.8769

Max Act: 0.6497. Min Act: -0.0000

Data Index: 570822 (C4 (Web Text))

Max Activating Token Index: 287