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

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

Neuron 3637 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: 0.3398. Min Range: -0.3398

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1066807 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2822. Min Act: -0.0000

Data Index: 887844 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2665. Min Act: -0.0000

Data Index: 370986 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2675. Min Act: -0.0000

Data Index: 935046 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2807. Min Act: -0.0000

Data Index: 971794 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2701. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2654. Min Act: -0.0000

Data Index: 523625 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1194092 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2824. Min Act: -0.0000

Data Index: 157331 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2605. Min Act: -0.0000

Data Index: 770113 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2704. Min Act: -0.0000

Data Index: 994648 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2590. Min Act: -0.0000

Data Index: 141212 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2641. Min Act: -0.0000

Data Index: 270014 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2582. Min Act: -0.0000

Data Index: 561571 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2437. Min Act: -0.0000

Data Index: 270972 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2626. Min Act: -0.0000

Data Index: 954870 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2579. Min Act: -0.0000

Data Index: 608090 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2494. Min Act: -0.0000

Data Index: 945121 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2463. Min Act: -0.0000

Data Index: 1200813 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.3398. Min Range: -0.3398

Max Act: 0.2464. Min Act: -0.0000

Data Index: 835997 (C4 (Web Text))

Max Activating Token Index: 685