Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3658 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1533295 (Python Code)

Max Activating Token Index: 846

Text #1

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1454943 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1572811 (Python Code)

Max Activating Token Index: 697

Text #3

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1410302 (Python Code)

Max Activating Token Index: 262

Text #4

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.6863. Min Act: -0.0001

Data Index: 1610848 (Python Code)

Max Activating Token Index: 877

Text #5

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1566318 (Python Code)

Max Activating Token Index: 234

Text #6

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.6318. Min Act: -0.0000

Data Index: 1591349 (Python Code)

Max Activating Token Index: 401

Text #7

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1510759 (Python Code)

Max Activating Token Index: 367

Text #8

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1472210 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1483167 (Python Code)

Max Activating Token Index: 706

Text #10

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1465939 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1590598 (Python Code)

Max Activating Token Index: 236

Text #12

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.6002. Min Act: -0.0001

Data Index: 1495169 (Python Code)

Max Activating Token Index: 1014

Text #13

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1547067 (Python Code)

Max Activating Token Index: 182

Text #14

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1488812 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1600004 (Python Code)

Max Activating Token Index: 796

Text #16

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.5644. Min Act: -0.0000

Data Index: 1631370 (Python Code)

Max Activating Token Index: 156

Text #17

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1602084 (Python Code)

Max Activating Token Index: 308

Text #18

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1369606 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 0.8124. Min Range: -0.8124

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1526470 (Python Code)

Max Activating Token Index: 307