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

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

Neuron 1962 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: 3.6940. Min Range: -3.6940

Max Act: 3.6940. Min Act: -0.1700

Data Index: 1048406 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6470. Min Act: -0.1700

Data Index: 421393 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6627. Min Act: -0.1700

Data Index: 100615 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1322830 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6470. Min Act: -0.1700

Data Index: 1215468 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6157. Min Act: -0.1700

Data Index: 1024520 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6314. Min Act: -0.1700

Data Index: 1357764 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6001. Min Act: -0.1700

Data Index: 745339 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6314. Min Act: -0.1700

Data Index: 1340629 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1181815 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6001. Min Act: -0.1700

Data Index: 156560 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.5844. Min Act: -0.1700

Data Index: 1074517 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6001. Min Act: -0.1700

Data Index: 471122 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.5844. Min Act: -0.1700

Data Index: 964318 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.5844. Min Act: -0.1700

Data Index: 443267 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.5844. Min Act: -0.1700

Data Index: 723796 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.6157. Min Act: -0.1700

Data Index: 1180106 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.5688. Min Act: -0.1700

Data Index: 392848 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.5688. Min Act: -0.1700

Data Index: 880414 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 3.6940. Min Range: -3.6940

Max Act: 3.5688. Min Act: -0.1700

Data Index: 78155 (C4 (Web Text))

Max Activating Token Index: 868