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

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

Neuron 988 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.2734. Min Act: -0.1700

Data Index: 1382888 (Python Code)

Max Activating Token Index: 51

Text #1

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.2734. Min Act: -0.1700

Data Index: 1537258 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.2576. Min Act: -0.1700

Data Index: 1546389 (Python Code)

Max Activating Token Index: 87

Text #3

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.2419. Min Act: -0.1700

Data Index: 1414073 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.2419. Min Act: -0.1700

Data Index: 1601200 (Python Code)

Max Activating Token Index: 101

Text #5

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.2105. Min Act: -0.1700

Data Index: 1401249 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1525779 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1472612 (Python Code)

Max Activating Token Index: 258

Text #8

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1790. Min Act: -0.1700

Data Index: 1375208 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1633. Min Act: -0.1700

Data Index: 1542215 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1633. Min Act: -0.1700

Data Index: 1576642 (Python Code)

Max Activating Token Index: 350

Text #11

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1633. Min Act: -0.1700

Data Index: 1631731 (Python Code)

Max Activating Token Index: 339

Text #12

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1608610 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1466360 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1567358 (Python Code)

Max Activating Token Index: 403

Text #15

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1318. Min Act: -0.1700

Data Index: 1423468 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1467107 (Python Code)

Max Activating Token Index: 20

Text #17

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1597506 (Python Code)

Max Activating Token Index: 197

Text #18

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1375258 (Python Code)

Max Activating Token Index: 202

Text #19

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.1475. Min Act: -0.1700

Data Index: 1398031 (Python Code)

Max Activating Token Index: 132