Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 485 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1349593 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1087477 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2384. Min Act: -0.0000

Data Index: 925 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2079. Min Act: -0.0000

Data Index: 811650 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2491. Min Act: -0.0000

Data Index: 903604 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2024. Min Act: -0.0000

Data Index: 440360 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1871. Min Act: -0.0000

Data Index: 79221 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2090. Min Act: -0.0000

Data Index: 801180 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1353774 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1878. Min Act: -0.0000

Data Index: 359920 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1597. Min Act: -0.0000

Data Index: 819762 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1239124 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1071215 (C4 (Web Text))

Max Activating Token Index: 628

Text #13

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1721. Min Act: -0.0000

Data Index: 271394 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1723. Min Act: -0.0000

Data Index: 813404 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1719. Min Act: -0.0000

Data Index: 833953 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1832. Min Act: -0.0000

Data Index: 142958 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1704. Min Act: -0.0000

Data Index: 544339 (C4 (Web Text))

Max Activating Token Index: 514

Text #18

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1530. Min Act: -0.0000

Data Index: 948276 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.3482. Min Range: -0.3482

Max Act: 0.1420. Min Act: -0.0000

Data Index: 81444 (C4 (Web Text))

Max Activating Token Index: 389