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

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

Neuron 581 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.4732. Min Act: -0.1700

Data Index: 231322 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3320. Min Act: -0.1700

Data Index: 958674 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.4105. Min Act: -0.1700

Data Index: 138955 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.4105. Min Act: -0.1700

Data Index: 450819 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.4105. Min Act: -0.1700

Data Index: 186237 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3791. Min Act: -0.1700

Data Index: 528568 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3791. Min Act: -0.1700

Data Index: 674830 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3477. Min Act: -0.1700

Data Index: 931465 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3006. Min Act: -0.1700

Data Index: 504569 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3320. Min Act: -0.1700

Data Index: 1136799 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3320. Min Act: -0.1700

Data Index: 1285744 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3163. Min Act: -0.1700

Data Index: 1056742 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3477. Min Act: -0.1700

Data Index: 947227 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3006. Min Act: -0.1700

Data Index: 1112292 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2692. Min Act: -0.1700

Data Index: 14875 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3006. Min Act: -0.1700

Data Index: 508825 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3006. Min Act: -0.1700

Data Index: 1069125 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2849. Min Act: -0.1700

Data Index: 62826 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.3163. Min Act: -0.1700

Data Index: 803033 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 3.4732. Min Range: -3.4732

Max Act: 3.2849. Min Act: -0.1700

Data Index: 244656 (C4 (Web Text))

Max Activating Token Index: 671