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

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

Neuron 296 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: 5.2467. Min Range: -5.2467

Max Act: 5.2467. Min Act: -0.1700

Data Index: 799640 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 5.2467. Min Range: -5.2467

Max Act: 5.2467. Min Act: -0.1700

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 5.2467. Min Range: -5.2467

Max Act: 5.1217. Min Act: -0.1700

Data Index: 1008223 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 5.2467. Min Range: -5.2467

Max Act: 5.0904. Min Act: -0.1700

Data Index: 986767 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 5.2467. Min Range: -5.2467

Max Act: 5.0904. Min Act: -0.1700

Data Index: 1153521 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 5.2467. Min Range: -5.2467

Max Act: 5.0279. Min Act: -0.1700

Data Index: 964023 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9967. Min Act: -0.1700

Data Index: 614105 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9654. Min Act: -0.1700

Data Index: 349545 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9654. Min Act: -0.1700

Data Index: 1171230 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9342. Min Act: -0.1700

Data Index: 604955 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 5.2467. Min Range: -5.2467

Max Act: 5.0279. Min Act: -0.1700

Data Index: 1233940 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9967. Min Act: -0.1700

Data Index: 436794 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.8717. Min Act: -0.1700

Data Index: 165975 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9654. Min Act: -0.1700

Data Index: 916227 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9342. Min Act: -0.1700

Data Index: 249760 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.8717. Min Act: -0.1700

Data Index: 593263 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9029. Min Act: -0.1700

Data Index: 554954 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.8404. Min Act: -0.1700

Data Index: 716055 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9029. Min Act: -0.1700

Data Index: 757130 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 5.2467. Min Range: -5.2467

Max Act: 4.9342. Min Act: -0.1700

Data Index: 227932 (C4 (Web Text))

Max Activating Token Index: 104