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

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

Neuron 482 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0996. Min Range: -3.0996

Max Act: 3.0838. Min Act: -0.1700

Data Index: 1286766 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 3.0996. Min Range: -3.0996

Max Act: 3.0996. Min Act: -0.1700

Data Index: 858020 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 3.0996. Min Range: -3.0996

Max Act: 3.0048. Min Act: -0.1700

Data Index: 401148 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.9890. Min Act: -0.1700

Data Index: 146265 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.9574. Min Act: -0.1700

Data Index: 1113699 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7986. Min Act: -0.1700

Data Index: 420768 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7508. Min Act: -0.1700

Data Index: 375304 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7667. Min Act: -0.1700

Data Index: 1293397 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7348. Min Act: -0.1700

Data Index: 894516 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7508. Min Act: -0.1700

Data Index: 11794 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7028. Min Act: -0.1700

Data Index: 917857 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7348. Min Act: -0.1700

Data Index: 951527 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7188. Min Act: -0.1700

Data Index: 1353738 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7028. Min Act: -0.1700

Data Index: 653681 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7188. Min Act: -0.1700

Data Index: 1305877 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7028. Min Act: -0.1700

Data Index: 379598 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7028. Min Act: -0.1700

Data Index: 239476 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.7028. Min Act: -0.1700

Data Index: 231963 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.6708. Min Act: -0.1700

Data Index: 884609 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 3.0996. Min Range: -3.0996

Max Act: 2.6708. Min Act: -0.1700

Data Index: 307675 (C4 (Web Text))

Max Activating Token Index: 888