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

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

Neuron 1162 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: 5.1139. Min Range: -5.1139

Max Act: 5.1139. Min Act: -0.1700

Data Index: 697141 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 5.1139. Min Range: -5.1139

Max Act: 5.0670. Min Act: -0.1700

Data Index: 936137 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 5.1139. Min Range: -5.1139

Max Act: 5.0826. Min Act: -0.1700

Data Index: 1048654 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.9733. Min Act: -0.1700

Data Index: 981161 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.8795. Min Act: -0.1700

Data Index: 260778 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 5.1139. Min Range: -5.1139

Max Act: 5.0045. Min Act: -0.1700

Data Index: 977980 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.9733. Min Act: -0.1700

Data Index: 805068 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.9108. Min Act: -0.1700

Data Index: 1056485 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.8951. Min Act: -0.1700

Data Index: 1258282 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.8639. Min Act: -0.1700

Data Index: 1115475 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.8639. Min Act: -0.1700

Data Index: 603379 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.8326. Min Act: -0.1700

Data Index: 387365 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.8326. Min Act: -0.1700

Data Index: 54787 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.8014. Min Act: -0.1700

Data Index: 128919 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.8170. Min Act: -0.1700

Data Index: 208477 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.7389. Min Act: -0.1700

Data Index: 699854 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.7858. Min Act: -0.1700

Data Index: 1290443 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.7701. Min Act: -0.1700

Data Index: 1044909 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.7076. Min Act: -0.1700

Data Index: 1229756 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 5.1139. Min Range: -5.1139

Max Act: 4.7233. Min Act: -0.1700

Data Index: 634382 (C4 (Web Text))

Max Activating Token Index: 137