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

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

Neuron 3482 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.3102. Min Act: -0.0000

Data Index: 759500 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2906. Min Act: -0.0000

Data Index: 776781 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.3002. Min Act: -0.0000

Data Index: 742532 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1280466 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2850. Min Act: -0.0000

Data Index: 129481 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2709. Min Act: -0.0000

Data Index: 422237 (C4 (Web Text))

Max Activating Token Index: 443

Text #6

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2110. Min Act: -0.0000

Data Index: 746535 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2836. Min Act: -0.0000

Data Index: 398625 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2728. Min Act: -0.0000

Data Index: 749444 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2662. Min Act: -0.0000

Data Index: 649861 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2757. Min Act: -0.0000

Data Index: 321500 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2615. Min Act: -0.0000

Data Index: 618149 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2540. Min Act: -0.0000

Data Index: 720307 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2717. Min Act: -0.0000

Data Index: 537936 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1246576 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2553. Min Act: -0.0000

Data Index: 906875 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2677. Min Act: -0.0000

Data Index: 428605 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2400. Min Act: -0.0000

Data Index: 990965 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1297664 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.3102. Min Range: -0.3102

Max Act: 0.2292. Min Act: -0.0000

Data Index: 382096 (C4 (Web Text))

Max Activating Token Index: 522