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

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

Neuron 1240 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: 3.8778. Min Range: -3.8778

Max Act: 3.8778. Min Act: -0.1700

Data Index: 1533760 (Python Code)

Max Activating Token Index: 943

Text #1

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7683. Min Act: -0.1700

Data Index: 1473122 (Python Code)

Max Activating Token Index: 839

Text #2

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.8309. Min Act: -0.1700

Data Index: 1572724 (Python Code)

Max Activating Token Index: 784

Text #3

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7683. Min Act: -0.1700

Data Index: 1508345 (Python Code)

Max Activating Token Index: 812

Text #4

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7526. Min Act: -0.1700

Data Index: 1647058 (Python Code)

Max Activating Token Index: 483

Text #5

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6901. Min Act: -0.1700

Data Index: 1524873 (Python Code)

Max Activating Token Index: 745

Text #6

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7214. Min Act: -0.1700

Data Index: 1482090 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7057. Min Act: -0.1700

Data Index: 1655183 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6431. Min Act: -0.1700

Data Index: 1556999 (Python Code)

Max Activating Token Index: 195

Text #9

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6744. Min Act: -0.1700

Data Index: 1452632 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6431. Min Act: -0.1700

Data Index: 1469513 (Python Code)

Max Activating Token Index: 300

Text #11

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6118. Min Act: -0.1700

Data Index: 1363731 (Python Code)

Max Activating Token Index: 660

Text #12

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.5805. Min Act: -0.1700

Data Index: 1650165 (Python Code)

Max Activating Token Index: 990

Text #13

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6431. Min Act: -0.1700

Data Index: 1434441 (Python Code)

Max Activating Token Index: 606

Text #14

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.5805. Min Act: -0.1700

Data Index: 1535465 (Python Code)

Max Activating Token Index: 331

Text #15

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6275. Min Act: -0.1700

Data Index: 1590370 (Python Code)

Max Activating Token Index: 729

Text #16

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6588. Min Act: -0.1700

Data Index: 1389916 (Python Code)

Max Activating Token Index: 366

Text #17

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.5961. Min Act: -0.1700

Data Index: 1388875 (Python Code)

Max Activating Token Index: 208

Text #18

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6744. Min Act: -0.1700

Data Index: 1404240 (Python Code)

Max Activating Token Index: 681

Text #19

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.6118. Min Act: -0.1700

Data Index: 1384399 (Python Code)

Max Activating Token Index: 170