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

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

Neuron 230 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.5042. Min Act: -0.1700

Data Index: 341255 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.4417. Min Act: -0.1700

Data Index: 764528 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.4417. Min Act: -0.1700

Data Index: 989704 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.4729. Min Act: -0.1700

Data Index: 403598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.3792. Min Act: -0.1700

Data Index: 951111 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.4104. Min Act: -0.1700

Data Index: 935149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.3792. Min Act: -0.1699

Data Index: 927093 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.3792. Min Act: -0.1700

Data Index: 1082713 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.3479. Min Act: -0.1700

Data Index: 702464 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2854. Min Act: -0.1700

Data Index: 412357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2854. Min Act: -0.1700

Data Index: 505322 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2854. Min Act: -0.1700

Data Index: 469331 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2854. Min Act: -0.1700

Data Index: 272759 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2854. Min Act: -0.1700

Data Index: 612260 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2854. Min Act: -0.1700

Data Index: 804744 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2541. Min Act: -0.1700

Data Index: 408710 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2541. Min Act: -0.1700

Data Index: 865720 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2541. Min Act: -0.1700

Data Index: 214506 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2541. Min Act: -0.1700

Data Index: 1050587 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.5042. Min Range: -4.5042

Max Act: 4.2229. Min Act: -0.1700

Data Index: 145058 (C4 (Web Text))

Max Activating Token Index: 1023