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

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

Neuron 1681 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0595. Min Range: -5.0595

Max Act: 5.0595. Min Act: -0.1700

Data Index: 273795 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.9345. Min Act: -0.1700

Data Index: 229770 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.8720. Min Act: -0.1700

Data Index: 184528 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.7157. Min Act: -0.1700

Data Index: 19176 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.6532. Min Act: -0.1700

Data Index: 219976 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.5595. Min Act: -0.1700

Data Index: 1318636 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.6063. Min Act: -0.1700

Data Index: 1344405 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.6063. Min Act: -0.1700

Data Index: 460577 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.5282. Min Act: -0.1700

Data Index: 587594 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.5907. Min Act: -0.1700

Data Index: 811804 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.5907. Min Act: -0.1700

Data Index: 944062 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.5438. Min Act: -0.1700

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.5282. Min Act: -0.1700

Data Index: 638681 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.5595. Min Act: -0.1700

Data Index: 418215 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.4970. Min Act: -0.1700

Data Index: 676209 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.5282. Min Act: -0.1700

Data Index: 918970 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.4813. Min Act: -0.1700

Data Index: 1145037 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.4657. Min Act: -0.1700

Data Index: 269033 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.4813. Min Act: -0.1700

Data Index: 531767 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 5.0595. Min Range: -5.0595

Max Act: 4.5751. Min Act: -0.1700

Data Index: 912065 (C4 (Web Text))

Max Activating Token Index: 524