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

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

Neuron 1102 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: 0.0885. Min Range: -0.0885

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1390742 (Python Code)

Max Activating Token Index: 356

Text #1

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1540855 (Python Code)

Max Activating Token Index: 118

Text #2

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1504548 (Python Code)

Max Activating Token Index: 176

Text #3

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1541186 (Python Code)

Max Activating Token Index: 348

Text #4

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1521990 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1501139 (Python Code)

Max Activating Token Index: 264

Text #6

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1396144 (Python Code)

Max Activating Token Index: 841

Text #7

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1400384 (Python Code)

Max Activating Token Index: 249

Text #8

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1373020 (Python Code)

Max Activating Token Index: 214

Text #9

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1448619 (Python Code)

Max Activating Token Index: 122

Text #10

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0624. Min Act: 0.0000

Data Index: 1568298 (Python Code)

Max Activating Token Index: 27

Text #11

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1564357 (Python Code)

Max Activating Token Index: 794

Text #12

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1564694 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1506769 (Python Code)

Max Activating Token Index: 351

Text #14

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0622. Min Act: -0.0003

Data Index: 1419444 (Python Code)

Max Activating Token Index: 893

Text #15

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1439632 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1573242 (Python Code)

Max Activating Token Index: 221

Text #17

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1606350 (Python Code)

Max Activating Token Index: 591

Text #18

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1566769 (Python Code)

Max Activating Token Index: 774

Text #19

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1500162 (Python Code)

Max Activating Token Index: 19