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

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

Neuron 1594 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: 0.2509. Min Range: -0.2509

Max Act: 0.2509. Min Act: -0.0000

Data Index: 741871 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1766. Min Act: -0.0000

Data Index: 583064 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1090600 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1115416 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1691. Min Act: -0.0000

Data Index: 584250 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1585. Min Act: -0.0000

Data Index: 739438 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1297476 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1601. Min Act: -0.0000

Data Index: 572163 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1606. Min Act: -0.0000

Data Index: 176733 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1573. Min Act: -0.0000

Data Index: 886841 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1576. Min Act: -0.0000

Data Index: 142358 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1517. Min Act: -0.0000

Data Index: 290731 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1624. Min Act: -0.0000

Data Index: 930720 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1059992 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1459. Min Act: -0.0000

Data Index: 3030 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1506. Min Act: -0.0000

Data Index: 34053 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1486. Min Act: -0.0000

Data Index: 127578 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1532. Min Act: -0.0000

Data Index: 412775 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1310718 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.2509. Min Range: -0.2509

Max Act: 0.1576. Min Act: -0.0000

Data Index: 217220 (C4 (Web Text))

Max Activating Token Index: 840