Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3371 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0936. Min Act: -0.0003

Data Index: 963693 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0865. Min Act: -0.0003

Data Index: 1264145 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0866. Min Act: -0.0003

Data Index: 1332830 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1001717 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0903. Min Act: -0.0003

Data Index: 731654 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0719. Min Act: -0.0004

Data Index: 1224077 (C4 (Web Text))

Max Activating Token Index: 353

Text #6

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0926. Min Act: -0.0003

Data Index: 154693 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0845. Min Act: -0.0003

Data Index: 212178 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0728. Min Act: -0.0003

Data Index: 996749 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1255554 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0770. Min Act: -0.0003

Data Index: 924229 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0738. Min Act: -0.0003

Data Index: 500765 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0792. Min Act: -0.0003

Data Index: 135036 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0848. Min Act: -0.0003

Data Index: 94150 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0658. Min Act: -0.0003

Data Index: 497442 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0757. Min Act: -0.0003

Data Index: 1118359 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0789. Min Act: -0.0003

Data Index: 330674 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0775. Min Act: -0.0003

Data Index: 153777 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0775. Min Act: -0.0003

Data Index: 1335451 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0888. Min Act: -0.0003

Data Index: 1002581 (C4 (Web Text))

Max Activating Token Index: 681