Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4826 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0728. Min Act: -0.0000

Data Index: 17609 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0617. Min Act: -0.0000

Data Index: 926255 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0574. Min Act: -0.0000

Data Index: 520374 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0553. Min Act: -0.0000

Data Index: 151491 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0615. Min Act: -0.0000

Data Index: 981064 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1000338 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0525. Min Act: -0.0000

Data Index: 33530 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0541. Min Act: -0.0000

Data Index: 1185978 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0554. Min Act: -0.0000

Data Index: 837205 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0512. Min Act: -0.0000

Data Index: 999638 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1578422 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0514. Min Act: -0.0000

Data Index: 897112 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1359519 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0488. Min Act: -0.0000

Data Index: 222410 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0481. Min Act: -0.0000

Data Index: 1356524 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1273043 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0476. Min Act: -0.0000

Data Index: 706711 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0426. Min Act: -0.0000

Data Index: 170754 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0436. Min Act: -0.0000

Data Index: 454688 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.0728. Min Range: -0.0728

Max Act: 0.0453. Min Act: -0.0000

Data Index: 447033 (C4 (Web Text))

Max Activating Token Index: 732