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

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

Neuron 2188 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0894. Min Act: -0.0003

Data Index: 200995 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0914. Min Act: -0.0003

Data Index: 807791 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0930. Min Act: -0.0003

Data Index: 207972 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0836. Min Act: -0.0003

Data Index: 828455 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0814. Min Act: -0.0003

Data Index: 1007082 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0780. Min Act: -0.0003

Data Index: 326314 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0776. Min Act: -0.0003

Data Index: 428576 (C4 (Web Text))

Max Activating Token Index: 777

Text #7

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0816. Min Act: -0.0003

Data Index: 827266 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0815. Min Act: -0.0003

Data Index: 1358006 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0740. Min Act: -0.0003

Data Index: 425644 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1216651 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0792. Min Act: -0.0003

Data Index: 70352 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0796. Min Act: -0.0003

Data Index: 124619 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0761. Min Act: -0.0003

Data Index: 616992 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0758. Min Act: -0.0003

Data Index: 600762 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0780. Min Act: -0.0003

Data Index: 202427 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0736. Min Act: -0.0003

Data Index: 659093 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0706. Min Act: -0.0003

Data Index: 363965 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0761. Min Act: -0.0003

Data Index: 954674 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0740. Min Act: -0.0003

Data Index: 123201 (C4 (Web Text))

Max Activating Token Index: 416