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

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

Neuron 61 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0006

Data Index: 1515940 (Python Code)

Max Activating Token Index: 794

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0731. Min Act: -0.0006

Data Index: 1529549 (Python Code)

Max Activating Token Index: 934

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0704. Min Act: -0.0006

Data Index: 1469606 (Python Code)

Max Activating Token Index: 720

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0691. Min Act: -0.0006

Data Index: 1415610 (Python Code)

Max Activating Token Index: 337

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0684. Min Act: -0.0006

Data Index: 1630996 (Python Code)

Max Activating Token Index: 68

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0676. Min Act: -0.0006

Data Index: 1442573 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0701. Min Act: -0.0006

Data Index: 1377262 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0684. Min Act: -0.0006

Data Index: 1593022 (Python Code)

Max Activating Token Index: 134

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0697. Min Act: -0.0006

Data Index: 1461424 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0699. Min Act: -0.0006

Data Index: 1584379 (Python Code)

Max Activating Token Index: 153

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0684. Min Act: -0.0006

Data Index: 1482353 (Python Code)

Max Activating Token Index: 258

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0642. Min Act: -0.0006

Data Index: 1502469 (Python Code)

Max Activating Token Index: 1011

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0693. Min Act: -0.0006

Data Index: 1540702 (Python Code)

Max Activating Token Index: 468

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0667. Min Act: -0.0006

Data Index: 1364483 (Python Code)

Max Activating Token Index: 905

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0675. Min Act: -0.0006

Data Index: 1480354 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0650. Min Act: -0.0006

Data Index: 1549395 (Python Code)

Max Activating Token Index: 349

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0670. Min Act: -0.0006

Data Index: 1579394 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0679. Min Act: -0.0006

Data Index: 1527194 (Python Code)

Max Activating Token Index: 346

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0681. Min Act: -0.0006

Data Index: 1639514 (Python Code)

Max Activating Token Index: 1022

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0652. Min Act: -0.0006

Data Index: 1492032 (Python Code)

Max Activating Token Index: 302