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

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

Neuron 1957 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.4629. Min Act: -0.0005

Data Index: 341997 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.4409. Min Act: -0.0005

Data Index: 776920 (C4 (Web Text))

Max Activating Token Index: 1005

Text #2

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.4320. Min Act: -0.0005

Data Index: 244040 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.4228. Min Act: -0.0005

Data Index: 1345489 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3800. Min Act: -0.0005

Data Index: 813366 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3660. Min Act: -0.0005

Data Index: 463955 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3777. Min Act: -0.0005

Data Index: 1210570 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3781. Min Act: -0.0005

Data Index: 292722 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3754. Min Act: -0.0005

Data Index: 466159 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3695. Min Act: -0.0005

Data Index: 263761 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3555. Min Act: -0.0005

Data Index: 891999 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3794. Min Act: -0.0005

Data Index: 1271653 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3633. Min Act: -0.0005

Data Index: 1140925 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3634. Min Act: -0.0005

Data Index: 1044795 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3477. Min Act: -0.0005

Data Index: 172725 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3693. Min Act: -0.0005

Data Index: 395565 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3540. Min Act: -0.0005

Data Index: 1196055 (C4 (Web Text))

Max Activating Token Index: 543

Text #17

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3557. Min Act: -0.0005

Data Index: 38616 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3522. Min Act: -0.0005

Data Index: 184486 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.4629. Min Range: -0.4629

Max Act: 0.3611. Min Act: -0.0005

Data Index: 337785 (C4 (Web Text))

Max Activating Token Index: 498