Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 608 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.5022. Min Act: -0.1700

Data Index: 406627 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.4397. Min Act: -0.1700

Data Index: 132972 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.3772. Min Act: -0.1700

Data Index: 1042609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.2210. Min Act: -0.1700

Data Index: 646418 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.2210. Min Act: -0.1700

Data Index: 788031 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.1585. Min Act: -0.1700

Data Index: 1135526 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.1272. Min Act: -0.1700

Data Index: 672002 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.0647. Min Act: -0.1700

Data Index: 663014 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.0647. Min Act: -0.1700

Data Index: 288345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.0647. Min Act: -0.1700

Data Index: 1254586 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.5022. Min Range: -5.5022

Max Act: 5.0647. Min Act: -0.1700

Data Index: 1203875 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.9085. Min Act: -0.1700

Data Index: 112098 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.9085. Min Act: -0.1700

Data Index: 976538 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.8460. Min Act: -0.1700

Data Index: 547119 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.8772. Min Act: -0.1700

Data Index: 1126207 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.9085. Min Act: -0.1700

Data Index: 112586 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.7522. Min Act: -0.1700

Data Index: 1035768 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.8460. Min Act: -0.1700

Data Index: 316558 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.7522. Min Act: -0.1700

Data Index: 7794 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.5022. Min Range: -5.5022

Max Act: 4.7835. Min Act: -0.1700

Data Index: 952117 (C4 (Web Text))

Max Activating Token Index: 1023