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

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

Neuron 1526 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: 5.4526. Min Range: -5.4526

Max Act: 5.4526. Min Act: -0.1700

Data Index: 1126898 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.2964. Min Act: -0.1700

Data Index: 1144007 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.2339. Min Act: -0.1700

Data Index: 794753 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.2026. Min Act: -0.1700

Data Index: 669953 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1714. Min Act: -0.1700

Data Index: 169583 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1401. Min Act: -0.1700

Data Index: 345258 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1089. Min Act: -0.1700

Data Index: 775976 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1401. Min Act: -0.1700

Data Index: 767564 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1089. Min Act: -0.1700

Data Index: 842837 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1089. Min Act: -0.1700

Data Index: 303157 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.0464. Min Act: -0.1700

Data Index: 349536 (C4 (Web Text))

Max Activating Token Index: 347

Text #11

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.0776. Min Act: -0.1699

Data Index: 621457 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.0464. Min Act: -0.1700

Data Index: 644738 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.0151. Min Act: -0.1700

Data Index: 914306 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.0151. Min Act: -0.1700

Data Index: 1044190 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.0151. Min Act: -0.1700

Data Index: 259170 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9839. Min Act: -0.1700

Data Index: 245915 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.0151. Min Act: -0.1700

Data Index: 311019 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9526. Min Act: -0.1700

Data Index: 494272 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9839. Min Act: -0.1700

Data Index: 907300 (C4 (Web Text))

Max Activating Token Index: 402