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

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

Neuron 1489 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: 5.9838. Min Range: -5.9838

Max Act: 5.9838. Min Act: -0.1700

Data Index: 30403 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.9838. Min Act: -0.1700

Data Index: 777445 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.9525. Min Act: -0.1700

Data Index: 37281 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.9213. Min Act: -0.1700

Data Index: 1223551 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.9525. Min Act: -0.1700

Data Index: 658165 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.9525. Min Act: -0.1700

Data Index: 1066003 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.9213. Min Act: -0.1700

Data Index: 126278 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.8900. Min Act: -0.1700

Data Index: 409373 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.8900. Min Act: -0.1700

Data Index: 1007190 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.9213. Min Act: -0.1700

Data Index: 1061366 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.8588. Min Act: -0.1700

Data Index: 973700 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.8588. Min Act: -0.1700

Data Index: 1289787 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.7650. Min Act: -0.1700

Data Index: 368391 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.7963. Min Act: -0.1700

Data Index: 1339747 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.7963. Min Act: -0.1700

Data Index: 318186 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.8588. Min Act: -0.1700

Data Index: 752394 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.8275. Min Act: -0.1700

Data Index: 1351333 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.7963. Min Act: -0.1700

Data Index: 772167 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.7963. Min Act: -0.1700

Data Index: 211628 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 5.9838. Min Range: -5.9838

Max Act: 5.7963. Min Act: -0.1700

Data Index: 366775 (C4 (Web Text))

Max Activating Token Index: 31