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

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

Neuron 309 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: 3.8799. Min Range: -3.8799

Max Act: 3.8799. Min Act: -0.1700

Data Index: 728702 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7548. Min Act: -0.1700

Data Index: 491962 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7235. Min Act: -0.1700

Data Index: 483384 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7235. Min Act: -0.1700

Data Index: 82504 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7235. Min Act: -0.1700

Data Index: 230786 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.7548. Min Act: -0.1699

Data Index: 873962 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1244187 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6922. Min Act: -0.1700

Data Index: 1166589 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6609. Min Act: -0.1700

Data Index: 350106 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6922. Min Act: -0.1700

Data Index: 800623 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6922. Min Act: -0.1700

Data Index: 1186823 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6922. Min Act: -0.1700

Data Index: 664705 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6296. Min Act: -0.1700

Data Index: 277797 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6609. Min Act: -0.1700

Data Index: 1202937 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6609. Min Act: -0.1700

Data Index: 574899 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6296. Min Act: -0.1700

Data Index: 798855 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6296. Min Act: -0.1700

Data Index: 1294481 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.5983. Min Act: -0.1700

Data Index: 601769 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.5983. Min Act: -0.1700

Data Index: 511365 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 3.8799. Min Range: -3.8799

Max Act: 3.6296. Min Act: -0.1700

Data Index: 627685 (C4 (Web Text))

Max Activating Token Index: 773