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

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

Neuron 2788 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.1445. Min Act: -0.0000

Data Index: 945218 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1103784 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.1322. Min Act: -0.0000

Data Index: 769044 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.1194. Min Act: -0.0000

Data Index: 334507 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.1555. Min Act: -0.0000

Data Index: 1005193 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0569. Min Act: -0.0000

Data Index: 1325522 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0660. Min Act: -0.0000

Data Index: 5017 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0403. Min Act: -0.0000

Data Index: 862690 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0673. Min Act: -0.0000

Data Index: 727578 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1302300 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0267. Min Act: -0.0000

Data Index: 52231 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 1.1694. Min Range: -1.1694

Max Act: 0.9973. Min Act: -0.0000

Data Index: 921663 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0201. Min Act: -0.0000

Data Index: 703460 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0461. Min Act: -0.0000

Data Index: 1004376 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0966. Min Act: -0.0000

Data Index: 1294960 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0337. Min Act: -0.0000

Data Index: 741752 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 1.1694. Min Range: -1.1694

Max Act: 1.0029. Min Act: -0.0000

Data Index: 423513 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 1.1694. Min Range: -1.1694

Max Act: 0.9727. Min Act: -0.0000

Data Index: 501669 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 1.1694. Min Range: -1.1694

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1282345 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.1694. Min Range: -1.1694

Max Act: 0.9696. Min Act: -0.0000

Data Index: 843065 (C4 (Web Text))

Max Activating Token Index: 14