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

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

Neuron 1692 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2144. Min Range: -4.2144

Max Act: 4.1270. Min Act: -0.0000

Data Index: 1577492 (Python Code)

Max Activating Token Index: 554

Text #1

Max Range: 4.2144. Min Range: -4.2144

Max Act: 3.7141. Min Act: -0.0000

Data Index: 1608177 (Python Code)

Max Activating Token Index: 204

Text #2

Max Range: 4.2144. Min Range: -4.2144

Max Act: 4.2144. Min Act: -0.0000

Data Index: 1453093 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 4.2144. Min Range: -4.2144

Max Act: 3.2635. Min Act: -0.0000

Data Index: 1423280 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.9835. Min Act: -0.0000

Data Index: 1580591 (Python Code)

Max Activating Token Index: 392

Text #5

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.9090. Min Act: -0.0000

Data Index: 1480562 (Python Code)

Max Activating Token Index: 265

Text #6

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.4583. Min Act: -0.0000

Data Index: 1517217 (Python Code)

Max Activating Token Index: 708

Text #7

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.6483. Min Act: -0.0000

Data Index: 1601756 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 4.2144. Min Range: -4.2144

Max Act: 3.2673. Min Act: -0.0000

Data Index: 1407190 (Python Code)

Max Activating Token Index: 468

Text #9

Max Range: 4.2144. Min Range: -4.2144

Max Act: 3.5569. Min Act: -0.0000

Data Index: 1390843 (Python Code)

Max Activating Token Index: 738

Text #10

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.5879. Min Act: -0.0000

Data Index: 1365034 (Python Code)

Max Activating Token Index: 900

Text #11

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.4927. Min Act: -0.0000

Data Index: 1372722 (Python Code)

Max Activating Token Index: 893

Text #12

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.4009. Min Act: -0.0000

Data Index: 1432200 (Python Code)

Max Activating Token Index: 796

Text #13

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.7180. Min Act: -0.0000

Data Index: 1403008 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.7050. Min Act: -0.0000

Data Index: 1493590 (Python Code)

Max Activating Token Index: 31

Text #15

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.6946. Min Act: -0.0000

Data Index: 1652883 (Python Code)

Max Activating Token Index: 584

Text #16

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.7153. Min Act: -0.0000

Data Index: 1650184 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.4908. Min Act: -0.0000

Data Index: 1533381 (Python Code)

Max Activating Token Index: 87

Text #18

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.9050. Min Act: -0.0000

Data Index: 1522599 (Python Code)

Max Activating Token Index: 884

Text #19

Max Range: 4.2144. Min Range: -4.2144

Max Act: 2.3452. Min Act: -0.0000

Data Index: 1380693 (Python Code)

Max Activating Token Index: 49