Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 659 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0904. Min Act: -0.0005

Data Index: 1513093 (Python Code)

Max Activating Token Index: 537

Text #1

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0866. Min Act: -0.0005

Data Index: 1254565 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0843. Min Act: -0.0005

Data Index: 284108 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0810. Min Act: -0.0005

Data Index: 866111 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0801. Min Act: -0.0005

Data Index: 989366 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0831. Min Act: -0.0005

Data Index: 744167 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0776. Min Act: -0.0005

Data Index: 588022 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0817. Min Act: -0.0005

Data Index: 251560 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0786. Min Act: -0.0005

Data Index: 1004580 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0769. Min Act: -0.0005

Data Index: 90789 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0771. Min Act: -0.0005

Data Index: 941476 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0800. Min Act: -0.0005

Data Index: 1161574 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0761. Min Act: -0.0005

Data Index: 129922 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0707. Min Act: -0.0005

Data Index: 721285 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0737. Min Act: -0.0005

Data Index: 1172393 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0794. Min Act: -0.0005

Data Index: 452761 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0767. Min Act: -0.0005

Data Index: 223701 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0726. Min Act: -0.0005

Data Index: 1287137 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0718. Min Act: -0.0005

Data Index: 1150103 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0760. Min Act: -0.0005

Data Index: 642923 (C4 (Web Text))

Max Activating Token Index: 638