Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2933 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.5032. Min Act: -0.0001

Data Index: 1385622 (Python Code)

Max Activating Token Index: 731

Text #1

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.2500. Min Act: -0.0001

Data Index: 1378686 (Python Code)

Max Activating Token Index: 179

Text #2

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1476243 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1428002 (Python Code)

Max Activating Token Index: 639

Text #4

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1503990 (Python Code)

Max Activating Token Index: 886

Text #5

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1413449 (Python Code)

Max Activating Token Index: 548

Text #6

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.2107. Min Act: -0.0001

Data Index: 397545 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1397370 (Python Code)

Max Activating Token Index: 322

Text #8

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.2097. Min Act: -0.0001

Data Index: 1529809 (Python Code)

Max Activating Token Index: 707

Text #9

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1612838 (Python Code)

Max Activating Token Index: 286

Text #10

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1925. Min Act: -0.0000

Data Index: 1635404 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1821. Min Act: -0.0000

Data Index: 849345 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1843. Min Act: -0.0001

Data Index: 1607035 (Python Code)

Max Activating Token Index: 570

Text #13

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1842. Min Act: -0.0001

Data Index: 1630018 (Python Code)

Max Activating Token Index: 863

Text #14

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1463042 (Python Code)

Max Activating Token Index: 452

Text #15

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1349999 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1746. Min Act: -0.0001

Data Index: 1442786 (Python Code)

Max Activating Token Index: 340

Text #17

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1606542 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1732. Min Act: -0.0001

Data Index: 1514009 (Python Code)

Max Activating Token Index: 745

Text #19

Max Range: 0.5032. Min Range: -0.5032

Max Act: 0.1841. Min Act: -0.0001

Data Index: 1501217 (Python Code)

Max Activating Token Index: 1020