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

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

Neuron 2929 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: 0.0886. Min Range: -0.0886

Max Act: 0.0886. Min Act: -0.0003

Data Index: 1624102 (Python Code)

Max Activating Token Index: 189

Text #1

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0770. Min Act: -0.0003

Data Index: 172421 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0781. Min Act: -0.0003

Data Index: 27504 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0766. Min Act: -0.0003

Data Index: 745745 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1307246 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0713. Min Act: -0.0003

Data Index: 1399482 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0704. Min Act: -0.0003

Data Index: 1223178 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0751. Min Act: -0.0003

Data Index: 443926 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1479710 (Python Code)

Max Activating Token Index: 913

Text #9

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0717. Min Act: -0.0003

Data Index: 1084030 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1189452 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0703. Min Act: -0.0003

Data Index: 789746 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0679. Min Act: -0.0004

Data Index: 1307168 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0653. Min Act: -0.0003

Data Index: 192547 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1419058 (Python Code)

Max Activating Token Index: 478

Text #15

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0699. Min Act: -0.0003

Data Index: 366781 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0663. Min Act: -0.0003

Data Index: 953388 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0667. Min Act: -0.0003

Data Index: 1289927 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1117580 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.0886. Min Range: -0.0886

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1638086 (Python Code)

Max Activating Token Index: 54