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

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

Neuron 639 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.6032. Min Act: -0.1700

Data Index: 1481471 (Python Code)

Max Activating Token Index: 753

Text #1

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.6032. Min Act: -0.1700

Data Index: 1558595 (Python Code)

Max Activating Token Index: 871

Text #2

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.5095. Min Act: -0.1700

Data Index: 1520933 (Python Code)

Max Activating Token Index: 839

Text #3

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4782. Min Act: -0.1700

Data Index: 1375189 (Python Code)

Max Activating Token Index: 613

Text #4

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.5095. Min Act: -0.1700

Data Index: 1366585 (Python Code)

Max Activating Token Index: 921

Text #5

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.5407. Min Act: -0.1700

Data Index: 1430298 (Python Code)

Max Activating Token Index: 731

Text #6

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4157. Min Act: -0.1700

Data Index: 1444319 (Python Code)

Max Activating Token Index: 816

Text #7

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.5095. Min Act: -0.1700

Data Index: 1516650 (Python Code)

Max Activating Token Index: 887

Text #8

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4470. Min Act: -0.1700

Data Index: 1508622 (Python Code)

Max Activating Token Index: 988

Text #9

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4782. Min Act: -0.1700

Data Index: 1586069 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4157. Min Act: -0.1700

Data Index: 1632371 (Python Code)

Max Activating Token Index: 721

Text #11

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4470. Min Act: -0.1700

Data Index: 1459994 (Python Code)

Max Activating Token Index: 700

Text #12

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.5095. Min Act: -0.1700

Data Index: 1570537 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4157. Min Act: -0.1700

Data Index: 1422918 (Python Code)

Max Activating Token Index: 917

Text #14

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4782. Min Act: -0.1700

Data Index: 1444491 (Python Code)

Max Activating Token Index: 1016

Text #15

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4157. Min Act: -0.1700

Data Index: 1610483 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.4157. Min Act: -0.1700

Data Index: 1494232 (Python Code)

Max Activating Token Index: 669

Text #17

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.3532. Min Act: -0.1700

Data Index: 1494539 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.2907. Min Act: -0.1700

Data Index: 1496019 (Python Code)

Max Activating Token Index: 224

Text #19

Max Range: 5.6032. Min Range: -5.6032

Max Act: 5.3220. Min Act: -0.1700

Data Index: 1580443 (Python Code)

Max Activating Token Index: 782