Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 622 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.0914. Min Range: -8.0914

Max Act: 8.0914. Min Act: -0.1700

Data Index: 1552798 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 8.0914. Min Range: -8.0914

Max Act: 8.0289. Min Act: -0.1700

Data Index: 1436619 (Python Code)

Max Activating Token Index: 566

Text #2

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.9039. Min Act: -0.1700

Data Index: 1647725 (Python Code)

Max Activating Token Index: 81

Text #3

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.8414. Min Act: -0.1700

Data Index: 1425965 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.9664. Min Act: -0.1700

Data Index: 1417069 (Python Code)

Max Activating Token Index: 89

Text #5

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.7789. Min Act: -0.1700

Data Index: 1530389 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.5914. Min Act: -0.1700

Data Index: 1550370 (Python Code)

Max Activating Token Index: 354

Text #7

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.7164. Min Act: -0.1700

Data Index: 1621287 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.6539. Min Act: -0.1700

Data Index: 1544630 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.5914. Min Act: -0.1700

Data Index: 1558580 (Python Code)

Max Activating Token Index: 328

Text #10

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.6539. Min Act: -0.1700

Data Index: 1508536 (Python Code)

Max Activating Token Index: 221

Text #11

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.5914. Min Act: -0.1700

Data Index: 1518327 (Python Code)

Max Activating Token Index: 387

Text #12

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.5914. Min Act: -0.1700

Data Index: 1615827 (Python Code)

Max Activating Token Index: 599

Text #13

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.5914. Min Act: -0.1700

Data Index: 1587085 (Python Code)

Max Activating Token Index: 292

Text #14

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.5289. Min Act: -0.1700

Data Index: 1640737 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.5914. Min Act: -0.1700

Data Index: 1431113 (Python Code)

Max Activating Token Index: 747

Text #16

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.4664. Min Act: -0.1700

Data Index: 1506430 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.5289. Min Act: -0.1700

Data Index: 1637514 (Python Code)

Max Activating Token Index: 56

Text #18

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.5289. Min Act: -0.1700

Data Index: 1606240 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 8.0914. Min Range: -8.0914

Max Act: 7.4664. Min Act: -0.1700

Data Index: 1468597 (Python Code)

Max Activating Token Index: 109