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

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

Neuron 4732 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 4.5038. Min Range: -4.5038

Max Act: 4.5038. Min Act: -0.0001

Data Index: 1608311 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.8502. Min Act: -0.0001

Data Index: 1380907 (Python Code)

Max Activating Token Index: 209

Text #2

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.5536. Min Act: -0.0001

Data Index: 1379500 (Python Code)

Max Activating Token Index: 121

Text #3

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.2166. Min Act: -0.0001

Data Index: 1371904 (Python Code)

Max Activating Token Index: 246

Text #4

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.1687. Min Act: -0.0001

Data Index: 1458901 (Python Code)

Max Activating Token Index: 204

Text #5

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.2726. Min Act: -0.0001

Data Index: 1656414 (Python Code)

Max Activating Token Index: 324

Text #6

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.1364. Min Act: -0.0001

Data Index: 1425924 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.1163. Min Act: -0.0001

Data Index: 1621762 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 4.5038. Min Range: -4.5038

Max Act: 2.9951. Min Act: -0.0001

Data Index: 1507240 (Python Code)

Max Activating Token Index: 880

Text #9

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.1153. Min Act: -0.0001

Data Index: 1488209 (Python Code)

Max Activating Token Index: 124

Text #10

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.1778. Min Act: -0.0001

Data Index: 1561552 (Python Code)

Max Activating Token Index: 280

Text #11

Max Range: 4.5038. Min Range: -4.5038

Max Act: 3.0088. Min Act: -0.0001

Data Index: 1514886 (Python Code)

Max Activating Token Index: 739

Text #12

Max Range: 4.5038. Min Range: -4.5038

Max Act: 2.9208. Min Act: -0.0001

Data Index: 1393643 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 4.5038. Min Range: -4.5038

Max Act: 2.9812. Min Act: -0.0001

Data Index: 1627952 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 4.5038. Min Range: -4.5038

Max Act: 2.9521. Min Act: -0.0001

Data Index: 1386464 (Python Code)

Max Activating Token Index: 160

Text #15

Max Range: 4.5038. Min Range: -4.5038

Max Act: 2.8462. Min Act: -0.0001

Data Index: 1463830 (Python Code)

Max Activating Token Index: 805

Text #16

Max Range: 4.5038. Min Range: -4.5038

Max Act: 2.9483. Min Act: -0.0001

Data Index: 1601561 (Python Code)

Max Activating Token Index: 170

Text #17

Max Range: 4.5038. Min Range: -4.5038

Max Act: 2.8595. Min Act: -0.0001

Data Index: 1457621 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 4.5038. Min Range: -4.5038

Max Act: 2.8800. Min Act: -0.0001

Data Index: 1513109 (Python Code)

Max Activating Token Index: 258

Text #19

Max Range: 4.5038. Min Range: -4.5038

Max Act: 2.7607. Min Act: -0.0001

Data Index: 1491774 (Python Code)

Max Activating Token Index: 96