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

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

Neuron 107 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.5684. Min Act: -0.1699

Data Index: 319143 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.5509. Min Act: -0.1699

Data Index: 557483 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.5246. Min Act: -0.1700

Data Index: 664939 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.5246. Min Act: -0.1700

Data Index: 468040 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.5246. Min Act: -0.1700

Data Index: 657142 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.5071. Min Act: -0.1700

Data Index: 549449 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4895. Min Act: -0.1700

Data Index: 668546 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4808. Min Act: -0.1699

Data Index: 1189018 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4808. Min Act: -0.1700

Data Index: 1238740 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4720. Min Act: -0.1700

Data Index: 1252101 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4720. Min Act: -0.1699

Data Index: 512577 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4632. Min Act: -0.1698

Data Index: 140917 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4544. Min Act: -0.1700

Data Index: 949421 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4632. Min Act: -0.1700

Data Index: 1004716 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4544. Min Act: -0.1700

Data Index: 404267 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4544. Min Act: -0.1700

Data Index: 1059300 (C4 (Web Text))

Max Activating Token Index: 1020

Text #16

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4544. Min Act: -0.1700

Data Index: 928314 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4544. Min Act: -0.1700

Data Index: 518890 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4368. Min Act: -0.1700

Data Index: 1075398 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.5684. Min Range: -1.5684

Max Act: 1.4456. Min Act: -0.1700

Data Index: 645371 (C4 (Web Text))

Max Activating Token Index: 1008