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

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

Neuron 1554 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: 5.6016. Min Range: -5.6016

Max Act: 5.6016. Min Act: -0.1700

Data Index: 814007 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 5.6016. Min Range: -5.6016

Max Act: 5.4453. Min Act: -0.1700

Data Index: 1282010 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 5.6016. Min Range: -5.6016

Max Act: 5.2891. Min Act: -0.1700

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 5.6016. Min Range: -5.6016

Max Act: 5.2891. Min Act: -0.1700

Data Index: 182439 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 5.6016. Min Range: -5.6016

Max Act: 5.1641. Min Act: -0.1700

Data Index: 198112 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 5.6016. Min Range: -5.6016

Max Act: 5.1328. Min Act: -0.1700

Data Index: 1203063 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 5.6016. Min Range: -5.6016

Max Act: 5.0391. Min Act: -0.1700

Data Index: 860913 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 5.6016. Min Range: -5.6016

Max Act: 5.0703. Min Act: -0.1700

Data Index: 480272 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.9766. Min Act: -0.1700

Data Index: 896920 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 5.6016. Min Range: -5.6016

Max Act: 5.0078. Min Act: -0.1700

Data Index: 991568 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.9766. Min Act: -0.1700

Data Index: 1143432 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 5.6016. Min Range: -5.6016

Max Act: 5.0078. Min Act: -0.1700

Data Index: 666529 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.9766. Min Act: -0.1700

Data Index: 915711 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.9141. Min Act: -0.1700

Data Index: 645215 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.8828. Min Act: -0.1700

Data Index: 1192802 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.8828. Min Act: -0.1700

Data Index: 265695 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.8828. Min Act: -0.1700

Data Index: 385337 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.8516. Min Act: -0.1700

Data Index: 557293 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.8203. Min Act: -0.1700

Data Index: 1023969 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 5.6016. Min Range: -5.6016

Max Act: 4.8516. Min Act: -0.1700

Data Index: 924899 (C4 (Web Text))

Max Activating Token Index: 824