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

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

Neuron 126 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2996. Min Range: -7.2996

Max Act: 7.2996. Min Act: -0.1700

Data Index: 625634 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 7.2996. Min Range: -7.2996

Max Act: 7.0183. Min Act: -0.1700

Data Index: 1349574 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.8621. Min Act: -0.1700

Data Index: 333758 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.8621. Min Act: -0.1700

Data Index: 785985 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.8621. Min Act: -0.1700

Data Index: 958042 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7371. Min Act: -0.1700

Data Index: 1120099 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7996. Min Act: -0.1700

Data Index: 218896 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7996. Min Act: -0.1700

Data Index: 707978 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7996. Min Act: -0.1700

Data Index: 457298 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7683. Min Act: -0.1700

Data Index: 903166 (C4 (Web Text))

Max Activating Token Index: 404

Text #10

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7683. Min Act: -0.1700

Data Index: 89344 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7683. Min Act: -0.1700

Data Index: 5944 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7371. Min Act: -0.1700

Data Index: 973401 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7058. Min Act: -0.1700

Data Index: 1348590 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7058. Min Act: -0.1700

Data Index: 1290248 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7058. Min Act: -0.1700

Data Index: 336021 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7371. Min Act: -0.1700

Data Index: 567661 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7371. Min Act: -0.1700

Data Index: 204422 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.7058. Min Act: -0.1700

Data Index: 806265 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 7.2996. Min Range: -7.2996

Max Act: 6.6746. Min Act: -0.1700

Data Index: 440906 (C4 (Web Text))

Max Activating Token Index: 748