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

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

Neuron 149 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: 3.8383. Min Range: -3.8383

Max Act: 3.8383. Min Act: -0.1700

Data Index: 1136954 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.8383. Min Act: -0.1700

Data Index: 895980 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.8383. Min Act: -0.1700

Data Index: 81352 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.8071. Min Act: -0.1700

Data Index: 489131 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.8383. Min Act: -0.1700

Data Index: 1244566 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7758. Min Act: -0.1700

Data Index: 772167 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7758. Min Act: -0.1700

Data Index: 685108 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7758. Min Act: -0.1700

Data Index: 413099 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7758. Min Act: -0.1700

Data Index: 1322736 (C4 (Web Text))

Max Activating Token Index: 868

Text #9

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7445. Min Act: -0.1700

Data Index: 1268507 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7758. Min Act: -0.1700

Data Index: 975214 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7758. Min Act: -0.1700

Data Index: 929012 (C4 (Web Text))

Max Activating Token Index: 598

Text #12

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.8071. Min Act: -0.1700

Data Index: 1280362 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7445. Min Act: -0.1700

Data Index: 438340 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7758. Min Act: -0.1700

Data Index: 697375 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7758. Min Act: -0.1700

Data Index: 926418 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7445. Min Act: -0.1700

Data Index: 141201 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7445. Min Act: -0.1700

Data Index: 860615 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7445. Min Act: -0.1700

Data Index: 62302 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 3.8383. Min Range: -3.8383

Max Act: 3.7445. Min Act: -0.1700

Data Index: 991126 (C4 (Web Text))

Max Activating Token Index: 844