Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 236 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.5519. Min Act: -0.1700

Data Index: 1525695 (Python Code)

Max Activating Token Index: 624

Text #1

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.4894. Min Act: -0.1700

Data Index: 1571478 (Python Code)

Max Activating Token Index: 490

Text #2

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.4582. Min Act: -0.1700

Data Index: 1446563 (Python Code)

Max Activating Token Index: 344

Text #3

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.4894. Min Act: -0.1700

Data Index: 1381380 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.4582. Min Act: -0.1700

Data Index: 1411900 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3957. Min Act: -0.1700

Data Index: 1600839 (Python Code)

Max Activating Token Index: 583

Text #6

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3644. Min Act: -0.1700

Data Index: 1433344 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.4269. Min Act: -0.1700

Data Index: 1415344 (Python Code)

Max Activating Token Index: 131

Text #8

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3332. Min Act: -0.1700

Data Index: 1381553 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3332. Min Act: -0.1700

Data Index: 1512347 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3644. Min Act: -0.1700

Data Index: 1540867 (Python Code)

Max Activating Token Index: 131

Text #11

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3644. Min Act: -0.1700

Data Index: 1487214 (Python Code)

Max Activating Token Index: 354

Text #12

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3957. Min Act: -0.1700

Data Index: 1528372 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3644. Min Act: -0.1700

Data Index: 1396452 (Python Code)

Max Activating Token Index: 999

Text #14

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3019. Min Act: -0.1700

Data Index: 1475152 (Python Code)

Max Activating Token Index: 541

Text #15

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3332. Min Act: -0.1700

Data Index: 1532849 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3332. Min Act: -0.1700

Data Index: 1486466 (Python Code)

Max Activating Token Index: 732

Text #17

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.3019. Min Act: -0.1700

Data Index: 1519367 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.2707. Min Act: -0.1700

Data Index: 1458508 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 5.5519. Min Range: -5.5519

Max Act: 5.2707. Min Act: -0.1700

Data Index: 1464320 (Python Code)

Max Activating Token Index: 453