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

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

Neuron 1900 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: 0.0941. Min Range: -0.0941

Max Act: 0.0941. Min Act: -0.0002

Data Index: 799018 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1274762 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0743. Min Act: -0.0002

Data Index: 792044 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0730. Min Act: -0.0002

Data Index: 439619 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0739. Min Act: -0.0002

Data Index: 205164 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0720. Min Act: -0.0002

Data Index: 868442 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0716. Min Act: -0.0002

Data Index: 662499 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0728. Min Act: -0.0002

Data Index: 802589 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0691. Min Act: -0.0002

Data Index: 217690 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0727. Min Act: -0.0002

Data Index: 2544 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1412163 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1386720 (Python Code)

Max Activating Token Index: 505

Text #12

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1275746 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0692. Min Act: -0.0002

Data Index: 1360870 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1163293 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0661. Min Act: -0.0002

Data Index: 595276 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1240184 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1472213 (Python Code)

Max Activating Token Index: 725

Text #18

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0678. Min Act: -0.0002

Data Index: 652190 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.0941. Min Range: -0.0941

Max Act: 0.0655. Min Act: -0.0002

Data Index: 131968 (C4 (Web Text))

Max Activating Token Index: 426