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

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

Neuron 1555 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.2524. Min Act: -0.1700

Data Index: 501713 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.2524. Min Act: -0.1700

Data Index: 1178785 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.1899. Min Act: -0.1700

Data Index: 976012 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.1586. Min Act: -0.1700

Data Index: 426736 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.1586. Min Act: -0.1700

Data Index: 157263 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.1274. Min Act: -0.1700

Data Index: 1204278 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.1274. Min Act: -0.1700

Data Index: 999593 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.1274. Min Act: -0.1700

Data Index: 285721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.1274. Min Act: -0.1700

Data Index: 101415 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.0648. Min Act: -0.1700

Data Index: 628233 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.2524. Min Range: -4.2524

Max Act: 4.0023. Min Act: -0.1700

Data Index: 890877 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.2524. Min Range: -4.2524

Max Act: 3.9398. Min Act: -0.1700

Data Index: 855172 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.2524. Min Range: -4.2524

Max Act: 3.9085. Min Act: -0.1700

Data Index: 1177545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.2524. Min Range: -4.2524

Max Act: 3.8303. Min Act: -0.1700

Data Index: 408061 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 4.2524. Min Range: -4.2524

Max Act: 3.8147. Min Act: -0.1700

Data Index: 730459 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 4.2524. Min Range: -4.2524

Max Act: 3.7678. Min Act: -0.1700

Data Index: 882067 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 4.2524. Min Range: -4.2524

Max Act: 3.7990. Min Act: -0.1700

Data Index: 514484 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 4.2524. Min Range: -4.2524

Max Act: 3.7678. Min Act: -0.1700

Data Index: 1055399 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 4.2524. Min Range: -4.2524

Max Act: 3.7208. Min Act: -0.1700

Data Index: 1249013 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 4.2524. Min Range: -4.2524

Max Act: 3.7052. Min Act: -0.1700

Data Index: 732434 (C4 (Web Text))

Max Activating Token Index: 72