Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 557 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.2048. Min Range: -5.2048

Max Act: 5.2048. Min Act: -0.1700

Data Index: 1278462 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 5.2048. Min Range: -5.2048

Max Act: 5.1423. Min Act: -0.1700

Data Index: 548180 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 5.2048. Min Range: -5.2048

Max Act: 5.0798. Min Act: -0.1700

Data Index: 909343 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 5.2048. Min Range: -5.2048

Max Act: 5.0798. Min Act: -0.1700

Data Index: 291174 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 5.2048. Min Range: -5.2048

Max Act: 5.0173. Min Act: -0.1700

Data Index: 929307 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.9861. Min Act: -0.1700

Data Index: 1150480 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.9236. Min Act: -0.1700

Data Index: 341138 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.8923. Min Act: -0.1700

Data Index: 489383 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.9236. Min Act: -0.1700

Data Index: 58854 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.8923. Min Act: -0.1700

Data Index: 390448 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.9236. Min Act: -0.1700

Data Index: 55063 (C4 (Web Text))

Max Activating Token Index: 488

Text #11

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.8923. Min Act: -0.1700

Data Index: 703027 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.8611. Min Act: -0.1699

Data Index: 667142 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.8923. Min Act: -0.1700

Data Index: 218827 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.8298. Min Act: -0.1700

Data Index: 927468 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.8298. Min Act: -0.1700

Data Index: 752053 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.8611. Min Act: -0.1700

Data Index: 282971 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.7986. Min Act: -0.1700

Data Index: 6688 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.7986. Min Act: -0.1700

Data Index: 637796 (C4 (Web Text))

Max Activating Token Index: 766

Text #19

Max Range: 5.2048. Min Range: -5.2048

Max Act: 4.7986. Min Act: -0.1700

Data Index: 247881 (C4 (Web Text))

Max Activating Token Index: 255