Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 656 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0782. Min Act: -0.0006

Data Index: 382188 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0664. Min Act: -0.0005

Data Index: 394905 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0677. Min Act: -0.0006

Data Index: 1265420 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0665. Min Act: -0.0006

Data Index: 46837 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0650. Min Act: -0.0006

Data Index: 1270482 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0629. Min Act: -0.0005

Data Index: 384410 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0640. Min Act: -0.0005

Data Index: 353113 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0633. Min Act: -0.0006

Data Index: 221008 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0631. Min Act: -0.0006

Data Index: 951971 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0644. Min Act: -0.0005

Data Index: 645035 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0612. Min Act: -0.0006

Data Index: 1261145 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0624. Min Act: -0.0006

Data Index: 1090546 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0634. Min Act: -0.0006

Data Index: 339706 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0623. Min Act: -0.0005

Data Index: 233206 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0619. Min Act: -0.0006

Data Index: 257488 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0608. Min Act: -0.0006

Data Index: 359959 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0619. Min Act: -0.0006

Data Index: 589353 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0616. Min Act: -0.0005

Data Index: 56532 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0627. Min Act: -0.0006

Data Index: 545609 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0616. Min Act: -0.0006

Data Index: 214339 (C4 (Web Text))

Max Activating Token Index: 780