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

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

Neuron 1075 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: 5.2942. Min Range: -5.2942

Max Act: 5.2942. Min Act: -0.1700

Data Index: 17240 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.2629. Min Act: -0.1700

Data Index: 220290 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.2629. Min Act: -0.1700

Data Index: 439663 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.2317. Min Act: -0.1700

Data Index: 1062363 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1692. Min Act: -0.1700

Data Index: 286446 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.2004. Min Act: -0.1700

Data Index: 1085017 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1379. Min Act: -0.1700

Data Index: 824870 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1379. Min Act: -0.1700

Data Index: 1188554 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1067. Min Act: -0.1699

Data Index: 164230 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1067. Min Act: -0.1700

Data Index: 740801 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1379. Min Act: -0.1700

Data Index: 108589 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1067. Min Act: -0.1700

Data Index: 982394 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1067. Min Act: -0.1699

Data Index: 1000033 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1067. Min Act: -0.1700

Data Index: 849254 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1379. Min Act: -0.1700

Data Index: 41851 (C4 (Web Text))

Max Activating Token Index: 943

Text #15

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.0754. Min Act: -0.1700

Data Index: 600077 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1067. Min Act: -0.1700

Data Index: 744112 (C4 (Web Text))

Max Activating Token Index: 316

Text #17

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.1379. Min Act: -0.1700

Data Index: 952815 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.0442. Min Act: -0.1700

Data Index: 1213494 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 5.2942. Min Range: -5.2942

Max Act: 5.0754. Min Act: -0.1700

Data Index: 1336516 (C4 (Web Text))

Max Activating Token Index: 179