Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 158 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.1233. Min Act: -0.1700

Data Index: 542953 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.1075. Min Act: -0.1700

Data Index: 590903 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0917. Min Act: -0.1700

Data Index: 941324 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.1075. Min Act: -0.1700

Data Index: 597966 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0917. Min Act: -0.1700

Data Index: 883480 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0917. Min Act: -0.1700

Data Index: 40577 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0760. Min Act: -0.1700

Data Index: 666360 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0760. Min Act: -0.1700

Data Index: 151865 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0602. Min Act: -0.1700

Data Index: 106229 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0444. Min Act: -0.1700

Data Index: 151960 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0286. Min Act: -0.1700

Data Index: 723919 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0444. Min Act: -0.1700

Data Index: 445925 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0444. Min Act: -0.1700

Data Index: 884911 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0286. Min Act: -0.1700

Data Index: 1276478 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0128. Min Act: -0.1700

Data Index: 274748 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0286. Min Act: -0.1700

Data Index: 429004 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0444. Min Act: -0.1700

Data Index: 639905 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0286. Min Act: -0.1700

Data Index: 1148900 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0286. Min Act: -0.1700

Data Index: 1327592 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0286. Min Act: -0.1700

Data Index: 1246894 (C4 (Web Text))

Max Activating Token Index: 736