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

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

Neuron 1527 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: 9.1773. Min Range: -9.1773

Max Act: 9.1773. Min Act: -0.1700

Data Index: 49760 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.9585. Min Act: -0.1700

Data Index: 247794 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.9898. Min Act: -0.1700

Data Index: 1101401 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.9585. Min Act: -0.1700

Data Index: 409554 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.9585. Min Act: -0.1700

Data Index: 21119 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.9273. Min Act: -0.1700

Data Index: 1009611 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8648. Min Act: -0.1700

Data Index: 1251671 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8648. Min Act: -0.1700

Data Index: 1032684 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8960. Min Act: -0.1700

Data Index: 87067 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8023. Min Act: -0.1700

Data Index: 1176479 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8648. Min Act: -0.1700

Data Index: 524976 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8023. Min Act: -0.1700

Data Index: 657787 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8648. Min Act: -0.1700

Data Index: 1338431 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.7085. Min Act: -0.1700

Data Index: 414787 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8335. Min Act: -0.1700

Data Index: 251929 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8648. Min Act: -0.1700

Data Index: 131098 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8023. Min Act: -0.1700

Data Index: 585563 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.7710. Min Act: -0.1700

Data Index: 1217463 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.7398. Min Act: -0.1700

Data Index: 158003 (C4 (Web Text))

Max Activating Token Index: 665

Text #19

Max Range: 9.1773. Min Range: -9.1773

Max Act: 8.8648. Min Act: -0.1700

Data Index: 548670 (C4 (Web Text))

Max Activating Token Index: 620