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

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

Neuron 973 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0273. Min Act: -0.1700

Data Index: 1013175 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0589. Min Act: -0.1700

Data Index: 837367 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0431. Min Act: -0.1700

Data Index: 471714 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0431. Min Act: -0.1700

Data Index: 40797 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0431. Min Act: -0.1700

Data Index: 856383 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0273. Min Act: -0.1700

Data Index: 539315 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0431. Min Act: -0.1700

Data Index: 817687 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0589. Min Act: -0.1700

Data Index: 169414 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0589. Min Act: -0.1700

Data Index: 606736 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0273. Min Act: -0.1700

Data Index: 315403 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0431. Min Act: -0.1700

Data Index: 502639 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0273. Min Act: -0.1700

Data Index: 870103 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0273. Min Act: -0.1700

Data Index: 215771 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0273. Min Act: -0.1700

Data Index: 240148 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0273. Min Act: -0.1700

Data Index: 1213708 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0273. Min Act: -0.1700

Data Index: 420076 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0115. Min Act: -0.1700

Data Index: 556664 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0115. Min Act: -0.1700

Data Index: 106328 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 3.0589. Min Range: -3.0589

Max Act: 2.9799. Min Act: -0.1700

Data Index: 732915 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 3.0589. Min Range: -3.0589

Max Act: 3.0115. Min Act: -0.1700

Data Index: 793411 (C4 (Web Text))

Max Activating Token Index: 45