Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 981 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.8533. Min Act: -0.0000

Data Index: 1547541 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.9420. Min Act: -0.0000

Data Index: 1394549 (Python Code)

Max Activating Token Index: 643

Text #2

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.8910. Min Act: -0.0000

Data Index: 1435629 (Python Code)

Max Activating Token Index: 765

Text #3

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.5691. Min Act: -0.0000

Data Index: 1502613 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.7687. Min Act: -0.0000

Data Index: 1539812 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.5773. Min Act: -0.0000

Data Index: 1420001 (Python Code)

Max Activating Token Index: 236

Text #6

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.6120. Min Act: -0.0000

Data Index: 1503310 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1566500 (Python Code)

Max Activating Token Index: 652

Text #8

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.3588. Min Act: -0.0000

Data Index: 1410466 (Python Code)

Max Activating Token Index: 499

Text #9

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.4407. Min Act: -0.0000

Data Index: 1579843 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.4015. Min Act: -0.0000

Data Index: 1396399 (Python Code)

Max Activating Token Index: 612

Text #11

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.2851. Min Act: -0.0000

Data Index: 1363009 (Python Code)

Max Activating Token Index: 713

Text #12

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.5083. Min Act: -0.0000

Data Index: 1619541 (Python Code)

Max Activating Token Index: 696

Text #13

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1533816 (Python Code)

Max Activating Token Index: 110

Text #14

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1394384 (Python Code)

Max Activating Token Index: 959

Text #15

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.2341. Min Act: -0.0000

Data Index: 1461434 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.4013. Min Act: -0.0000

Data Index: 1546640 (Python Code)

Max Activating Token Index: 83

Text #17

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1394009 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.3085. Min Act: -0.0000

Data Index: 1632948 (Python Code)

Max Activating Token Index: 678

Text #19

Max Range: 1.9420. Min Range: -1.9420

Max Act: 1.3013. Min Act: -0.0000

Data Index: 1521150 (Python Code)

Max Activating Token Index: 45