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

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

Neuron 830 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0828. Min Range: -5.0828

Max Act: 5.0828. Min Act: -0.1700

Data Index: 48894 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.8953. Min Act: -0.1700

Data Index: 76427 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.8640. Min Act: -0.1700

Data Index: 956621 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.7703. Min Act: -0.1700

Data Index: 1262087 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.7390. Min Act: -0.1700

Data Index: 835999 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.7078. Min Act: -0.1700

Data Index: 513461 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.6765. Min Act: -0.1700

Data Index: 1014944 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.6140. Min Act: -0.1700

Data Index: 803550 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.6765. Min Act: -0.1700

Data Index: 151810 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.6453. Min Act: -0.1700

Data Index: 739231 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.5828. Min Act: -0.1700

Data Index: 1300184 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.6140. Min Act: -0.1700

Data Index: 1141283 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.5828. Min Act: -0.1700

Data Index: 821040 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.6140. Min Act: -0.1700

Data Index: 81444 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.5203. Min Act: -0.1700

Data Index: 1275939 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.5515. Min Act: -0.1700

Data Index: 259178 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.4890. Min Act: -0.1700

Data Index: 218922 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.5203. Min Act: -0.1700

Data Index: 1050545 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.5515. Min Act: -0.1700

Data Index: 863288 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 5.0828. Min Range: -5.0828

Max Act: 4.5515. Min Act: -0.1700

Data Index: 739209 (C4 (Web Text))

Max Activating Token Index: 880