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

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

Neuron 475 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: 5.6581. Min Range: -5.6581

Max Act: 5.6581. Min Act: -0.1699

Data Index: 355840 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.6581. Min Act: -0.1700

Data Index: 67623 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5956. Min Act: -0.1700

Data Index: 200354 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5956. Min Act: -0.1699

Data Index: 617649 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.5018. Min Act: -0.1698

Data Index: 507364 (C4 (Web Text))

Max Activating Token Index: 641

Text #5

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4081. Min Act: -0.1698

Data Index: 495180 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.4393. Min Act: -0.1700

Data Index: 496512 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.2518. Min Act: -0.1700

Data Index: 34391 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.0643. Min Act: -0.1700

Data Index: 895778 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.0331. Min Act: -0.1700

Data Index: 179061 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 5.6581. Min Range: -5.6581

Max Act: 4.9706. Min Act: -0.1699

Data Index: 1130330 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 5.6581. Min Range: -5.6581

Max Act: 4.9393. Min Act: -0.1700

Data Index: 1243026 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 5.6581. Min Range: -5.6581

Max Act: 4.9081. Min Act: -0.1700

Data Index: 1320553 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 5.6581. Min Range: -5.6581

Max Act: 4.9393. Min Act: -0.1700

Data Index: 447659 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 5.6581. Min Range: -5.6581

Max Act: 4.9393. Min Act: -0.1699

Data Index: 1355456 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 5.6581. Min Range: -5.6581

Max Act: 4.8143. Min Act: -0.1700

Data Index: 1348468 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 5.6581. Min Range: -5.6581

Max Act: 4.9393. Min Act: -0.1700

Data Index: 921966 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 5.6581. Min Range: -5.6581

Max Act: 5.0018. Min Act: -0.1700

Data Index: 1117682 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 5.6581. Min Range: -5.6581

Max Act: 4.9081. Min Act: -0.1700

Data Index: 10574 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 5.6581. Min Range: -5.6581

Max Act: 4.8768. Min Act: -0.1700

Data Index: 262811 (C4 (Web Text))

Max Activating Token Index: 640