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

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

Neuron 1401 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: 0.0611. Min Range: -0.0611

Max Act: 0.0566. Min Act: -0.0002

Data Index: 407836 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0001

Data Index: 277472 (C4 (Web Text))

Max Activating Token Index: 445

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0551. Min Act: -0.0002

Data Index: 676056 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0519. Min Act: -0.0002

Data Index: 94459 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0568. Min Act: -0.0002

Data Index: 1185412 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1311792 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0554. Min Act: -0.0002

Data Index: 149421 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0507. Min Act: -0.0002

Data Index: 660977 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0531. Min Act: -0.0002

Data Index: 279801 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1351114 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0492. Min Act: -0.0002

Data Index: 807702 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0539. Min Act: -0.0002

Data Index: 844804 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1330583 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1280072 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0478. Min Act: -0.0001

Data Index: 138545 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0524. Min Act: -0.0002

Data Index: 578304 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0446. Min Act: -0.0002

Data Index: 816504 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1571146 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0429. Min Act: -0.0002

Data Index: 987570 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0491. Min Act: -0.0002

Data Index: 721686 (C4 (Web Text))

Max Activating Token Index: 844