Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 828 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0001

Data Index: 622419 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0662. Min Act: -0.0001

Data Index: 59188 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0607. Min Act: -0.0001

Data Index: 315154 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1282009 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0649. Min Act: -0.0001

Data Index: 645175 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0637. Min Act: -0.0001

Data Index: 596543 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0636. Min Act: -0.0001

Data Index: 668933 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1429141 (Python Code)

Max Activating Token Index: 367

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1086384 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0617. Min Act: -0.0001

Data Index: 1322925 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1184497 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1198487 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0591. Min Act: -0.0001

Data Index: 442375 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0562. Min Act: -0.0001

Data Index: 1413320 (Python Code)

Max Activating Token Index: 822

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0590. Min Act: -0.0001

Data Index: 221723 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1253499 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0574. Min Act: -0.0001

Data Index: 450930 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0563. Min Act: -0.0001

Data Index: 234203 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0583. Min Act: -0.0001

Data Index: 786880 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1245850 (C4 (Web Text))

Max Activating Token Index: 328