Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 506 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0650. Min Act: -0.0003

Data Index: 743349 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1648432 (Python Code)

Max Activating Token Index: 342

Text #2

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0624. Min Act: -0.0003

Data Index: 1632985 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1407748 (Python Code)

Max Activating Token Index: 587

Text #4

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0597. Min Act: -0.0004

Data Index: 1182147 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1494007 (Python Code)

Max Activating Token Index: 813

Text #6

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1363782 (Python Code)

Max Activating Token Index: 654

Text #7

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1230167 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0562. Min Act: -0.0003

Data Index: 233348 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1435184 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0592. Min Act: -0.0004

Data Index: 210444 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0560. Min Act: -0.0003

Data Index: 576201 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0574. Min Act: -0.0003

Data Index: 333425 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1284570 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0548. Min Act: -0.0003

Data Index: 107130 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1331831 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0565. Min Act: -0.0004

Data Index: 1065949 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0550. Min Act: -0.0003

Data Index: 64114 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0544. Min Act: -0.0003

Data Index: 944468 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.0650. Min Range: -0.0650

Max Act: 0.0551. Min Act: -0.0003

Data Index: 1469784 (Python Code)

Max Activating Token Index: 89