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

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

Neuron 473 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: 5.3999. Min Range: -5.3999

Max Act: 5.3999. Min Act: -0.1700

Data Index: 116091 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.3061. Min Act: -0.1700

Data Index: 100669 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.2749. Min Act: -0.1700

Data Index: 784471 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.2749. Min Act: -0.1700

Data Index: 1055842 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1811. Min Act: -0.1700

Data Index: 1186928 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.2124. Min Act: -0.1700

Data Index: 1256146 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1186. Min Act: -0.1700

Data Index: 992023 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1499. Min Act: -0.1700

Data Index: 30748 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1186. Min Act: -0.1700

Data Index: 82872 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.1499. Min Act: -0.1700

Data Index: 819920 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0561. Min Act: -0.1700

Data Index: 345439 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0874. Min Act: -0.1700

Data Index: 431333 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0561. Min Act: -0.1700

Data Index: 64344 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0249. Min Act: -0.1700

Data Index: 816181 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0249. Min Act: -0.1700

Data Index: 698911 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0874. Min Act: -0.1700

Data Index: 489918 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 5.3999. Min Range: -5.3999

Max Act: 4.9936. Min Act: -0.1700

Data Index: 1102906 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0561. Min Act: -0.1700

Data Index: 764845 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0561. Min Act: -0.1700

Data Index: 253668 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 5.3999. Min Range: -5.3999

Max Act: 5.0249. Min Act: -0.1700

Data Index: 130787 (C4 (Web Text))

Max Activating Token Index: 315