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

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

Neuron 872 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: 9.0625. Min Range: -9.0625

Max Act: 9.0312. Min Act: -0.1700

Data Index: 1249642 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.9687. Min Act: -0.1700

Data Index: 571895 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 9.0625. Min Range: -9.0625

Max Act: 9.0625. Min Act: -0.1700

Data Index: 382663 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 9.0625. Min Range: -9.0625

Max Act: 9.0625. Min Act: -0.1700

Data Index: 914990 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.8125. Min Act: -0.1700

Data Index: 377196 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.9687. Min Act: -0.1699

Data Index: 450678 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.8750. Min Act: -0.1700

Data Index: 781676 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 9.0625. Min Range: -9.0625

Max Act: 9.0000. Min Act: -0.1700

Data Index: 70036 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.9687. Min Act: -0.1700

Data Index: 1182148 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.8750. Min Act: -0.1700

Data Index: 530496 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.9062. Min Act: -0.1700

Data Index: 933371 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.5937. Min Act: -0.1700

Data Index: 763668 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.8125. Min Act: -0.1700

Data Index: 747697 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.6875. Min Act: -0.1700

Data Index: 1111095 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.7500. Min Act: -0.1700

Data Index: 1261123 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.7812. Min Act: -0.1699

Data Index: 20781 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.7187. Min Act: -0.1700

Data Index: 952633 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.6250. Min Act: -0.1700

Data Index: 391988 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.6562. Min Act: -0.1699

Data Index: 782491 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 9.0625. Min Range: -9.0625

Max Act: 8.6562. Min Act: -0.1700

Data Index: 198701 (C4 (Web Text))

Max Activating Token Index: 648