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

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

Neuron 1196 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: 0.0591. Min Range: -0.0591

Max Act: 0.0591. Min Act: -0.0002

Data Index: 110930 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0582. Min Act: -0.0002

Data Index: 219159 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0591. Min Act: -0.0002

Data Index: 937475 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0567. Min Act: -0.0002

Data Index: 861038 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1075166 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0549. Min Act: -0.0002

Data Index: 114617 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0534. Min Act: -0.0002

Data Index: 946929 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0537. Min Act: -0.0002

Data Index: 417014 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0562. Min Act: -0.0002

Data Index: 480098 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1113132 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1181836 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0502. Min Act: -0.0002

Data Index: 227522 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0522. Min Act: -0.0002

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1296655 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0536. Min Act: -0.0002

Data Index: 206503 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1119618 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0554. Min Act: -0.0002

Data Index: 439408 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1164180 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1267140 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0515. Min Act: -0.0002

Data Index: 368616 (C4 (Web Text))

Max Activating Token Index: 144