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

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

Neuron 1949 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0629. Min Act: -0.0002

Data Index: 535891 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0586. Min Act: -0.0002

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0622. Min Act: -0.0002

Data Index: 906666 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1294579 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0623. Min Act: -0.0002

Data Index: 81877 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0002

Data Index: 639352 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0561. Min Act: -0.0002

Data Index: 218896 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0565. Min Act: -0.0002

Data Index: 110140 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0553. Min Act: -0.0002

Data Index: 707799 (C4 (Web Text))

Max Activating Token Index: 188

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0587. Min Act: -0.0002

Data Index: 958383 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0600. Min Act: -0.0002

Data Index: 767759 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0610. Min Act: -0.0002

Data Index: 957001 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0570. Min Act: -0.0002

Data Index: 437647 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0570. Min Act: -0.0002

Data Index: 802149 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0573. Min Act: -0.0002

Data Index: 940133 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0564. Min Act: -0.0002

Data Index: 737806 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1165536 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0548. Min Act: -0.0002

Data Index: 336399 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0563. Min Act: -0.0002

Data Index: 198522 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0555. Min Act: -0.0002

Data Index: 124191 (C4 (Web Text))

Max Activating Token Index: 41