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

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

Neuron 648 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.3345. Min Act: -0.1700

Data Index: 760611 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.1783. Min Act: -0.1700

Data Index: 655726 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.1470. Min Act: -0.1700

Data Index: 194792 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.1470. Min Act: -0.1700

Data Index: 221485 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.1470. Min Act: -0.1700

Data Index: 1002380 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.1470. Min Act: -0.1700

Data Index: 400770 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.1470. Min Act: -0.1700

Data Index: 1213136 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.1470. Min Act: -0.1700

Data Index: 36927 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.0845. Min Act: -0.1700

Data Index: 904083 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.0220. Min Act: -0.1700

Data Index: 1040028 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.0533. Min Act: -0.1700

Data Index: 364724 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.0220. Min Act: -0.1700

Data Index: 1265993 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 5.3345. Min Range: -5.3345

Max Act: 4.9908. Min Act: -0.1700

Data Index: 719176 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.0533. Min Act: -0.1700

Data Index: 5193 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 5.3345. Min Range: -5.3345

Max Act: 4.9908. Min Act: -0.1700

Data Index: 1178658 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.0533. Min Act: -0.1700

Data Index: 661083 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.0533. Min Act: -0.1700

Data Index: 1104956 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 5.3345. Min Range: -5.3345

Max Act: 4.9595. Min Act: -0.1700

Data Index: 806550 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 5.3345. Min Range: -5.3345

Max Act: 5.0220. Min Act: -0.1700

Data Index: 544028 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 5.3345. Min Range: -5.3345

Max Act: 4.9283. Min Act: -0.1700

Data Index: 974520 (C4 (Web Text))

Max Activating Token Index: 696