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

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

Neuron 371 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: 0.0847. Min Range: -0.0847

Max Act: 0.0821. Min Act: -0.0005

Data Index: 66007 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0810. Min Act: -0.0005

Data Index: 260090 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0816. Min Act: -0.0005

Data Index: 1190985 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0847. Min Act: -0.0005

Data Index: 726325 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0807. Min Act: -0.0005

Data Index: 1358383 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0768. Min Act: -0.0005

Data Index: 962992 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0761. Min Act: -0.0005

Data Index: 816323 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0748. Min Act: -0.0005

Data Index: 1054659 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0757. Min Act: -0.0005

Data Index: 1026981 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0763. Min Act: -0.0005

Data Index: 120823 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0782. Min Act: -0.0005

Data Index: 140346 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0758. Min Act: -0.0005

Data Index: 521536 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0713. Min Act: -0.0005

Data Index: 24674 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0735. Min Act: -0.0005

Data Index: 248674 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0767. Min Act: -0.0005

Data Index: 802804 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0746. Min Act: -0.0005

Data Index: 681332 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0758. Min Act: -0.0005

Data Index: 496179 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0733. Min Act: -0.0005

Data Index: 587331 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0744. Min Act: -0.0005

Data Index: 593090 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0724. Min Act: -0.0005

Data Index: 1031824 (C4 (Web Text))

Max Activating Token Index: 694