Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 636 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3747. Min Act: -0.0001

Data Index: 1080530 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3159. Min Act: -0.0001

Data Index: 574298 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3249. Min Act: -0.0001

Data Index: 1262630 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3030. Min Act: -0.0001

Data Index: 185780 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2957. Min Act: -0.0001

Data Index: 540680 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2825. Min Act: -0.0001

Data Index: 426203 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2882. Min Act: -0.0001

Data Index: 183816 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2693. Min Act: -0.0001

Data Index: 1047240 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2690. Min Act: -0.0001

Data Index: 1009049 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2850. Min Act: -0.0001

Data Index: 1225895 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2567. Min Act: -0.0001

Data Index: 469762 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2743. Min Act: -0.0001

Data Index: 985828 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2831. Min Act: -0.0001

Data Index: 592623 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2764. Min Act: -0.0001

Data Index: 714834 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2593. Min Act: -0.0001

Data Index: 1333223 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2647. Min Act: -0.0001

Data Index: 434561 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2707. Min Act: -0.0001

Data Index: 705161 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2613. Min Act: -0.0001

Data Index: 137294 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2701. Min Act: -0.0001

Data Index: 213573 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2656. Min Act: -0.0001

Data Index: 614706 (C4 (Web Text))

Max Activating Token Index: 273