Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 850 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0002

Data Index: 223028 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0851. Min Act: -0.0003

Data Index: 250995 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0782. Min Act: -0.0003

Data Index: 252068 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0746. Min Act: -0.0003

Data Index: 698655 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1216230 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0678. Min Act: -0.0002

Data Index: 547604 (C4 (Web Text))

Max Activating Token Index: 894

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0755. Min Act: -0.0003

Data Index: 594920 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0696. Min Act: -0.0003

Data Index: 766230 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0676. Min Act: -0.0003

Data Index: 1096371 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0694. Min Act: -0.0003

Data Index: 974714 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0681. Min Act: -0.0003

Data Index: 384131 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0647. Min Act: -0.0003

Data Index: 1157793 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1038001 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0626. Min Act: -0.0003

Data Index: 628660 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0627. Min Act: -0.0003

Data Index: 827850 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0620. Min Act: -0.0003

Data Index: 977785 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0600. Min Act: -0.0003

Data Index: 185565 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0624. Min Act: -0.0003

Data Index: 48148 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0620. Min Act: -0.0003

Data Index: 1014084 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0621. Min Act: -0.0003

Data Index: 909541 (C4 (Web Text))

Max Activating Token Index: 849