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

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

Neuron 616 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: 5.0643. Min Range: -5.0643

Max Act: 5.0643. Min Act: -0.1700

Data Index: 582306 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.9706. Min Act: -0.1700

Data Index: 750154 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.9706. Min Act: -0.1700

Data Index: 936126 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.9393. Min Act: -0.1700

Data Index: 153788 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7831. Min Act: -0.1700

Data Index: 1216760 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.8768. Min Act: -0.1700

Data Index: 932301 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.8456. Min Act: -0.1700

Data Index: 754353 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.8768. Min Act: -0.1700

Data Index: 773703 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.8768. Min Act: -0.1700

Data Index: 724708 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7206. Min Act: -0.1700

Data Index: 284950 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7518. Min Act: -0.1700

Data Index: 774393 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7831. Min Act: -0.1700

Data Index: 1265621 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7518. Min Act: -0.1700

Data Index: 271756 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7206. Min Act: -0.1700

Data Index: 849871 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7831. Min Act: -0.1700

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7206. Min Act: -0.1700

Data Index: 923339 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7831. Min Act: -0.1700

Data Index: 236308 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7206. Min Act: -0.1700

Data Index: 1146805 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.6893. Min Act: -0.1700

Data Index: 681089 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 5.0643. Min Range: -5.0643

Max Act: 4.7206. Min Act: -0.1700

Data Index: 656750 (C4 (Web Text))

Max Activating Token Index: 933