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

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

Neuron 1604 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.6102. Min Act: -0.1700

Data Index: 408373 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.5476. Min Act: -0.1700

Data Index: 535666 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.5476. Min Act: -0.1700

Data Index: 524320 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.5163. Min Act: -0.1700

Data Index: 1044906 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.5319. Min Act: -0.1698

Data Index: 640788 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.5163. Min Act: -0.1700

Data Index: 246373 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4849. Min Act: -0.1700

Data Index: 265962 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4693. Min Act: -0.1700

Data Index: 178381 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4536. Min Act: -0.1700

Data Index: 974751 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4536. Min Act: -0.1700

Data Index: 798158 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4536. Min Act: -0.1700

Data Index: 1279330 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4379. Min Act: -0.1700

Data Index: 220623 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4222. Min Act: -0.1700

Data Index: 972771 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4379. Min Act: -0.1700

Data Index: 197270 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4066. Min Act: -0.1699

Data Index: 84610 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4066. Min Act: -0.1700

Data Index: 285950 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4222. Min Act: -0.1700

Data Index: 723109 (C4 (Web Text))

Max Activating Token Index: 73

Text #17

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4379. Min Act: -0.1700

Data Index: 1075111 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4066. Min Act: -0.1700

Data Index: 1289651 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 3.6102. Min Range: -3.6102

Max Act: 3.4066. Min Act: -0.1700

Data Index: 487116 (C4 (Web Text))

Max Activating Token Index: 904