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

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

Neuron 794 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.7214. Min Act: -0.1700

Data Index: 397699 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.7214. Min Act: -0.1700

Data Index: 290785 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.5962. Min Act: -0.1700

Data Index: 1103942 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.5962. Min Act: -0.1700

Data Index: 575418 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.5022. Min Act: -0.1700

Data Index: 439366 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.5022. Min Act: -0.1700

Data Index: 1348851 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.4709. Min Act: -0.1700

Data Index: 1019351 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.4709. Min Act: -0.1700

Data Index: 124 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.4709. Min Act: -0.1700

Data Index: 688153 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.4709. Min Act: -0.1700

Data Index: 1201908 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.4082. Min Act: -0.1700

Data Index: 1229307 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.4082. Min Act: -0.1700

Data Index: 1007106 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.4082. Min Act: -0.1700

Data Index: 454220 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.3454. Min Act: -0.1700

Data Index: 261772 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.3768. Min Act: -0.1700

Data Index: 1218927 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.4082. Min Act: -0.1700

Data Index: 1122972 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.3768. Min Act: -0.1700

Data Index: 852357 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.3768. Min Act: -0.1700

Data Index: 748547 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.3768. Min Act: -0.1700

Data Index: 1048890 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 3.7214. Min Range: -3.7214

Max Act: 3.3454. Min Act: -0.1700

Data Index: 933609 (C4 (Web Text))

Max Activating Token Index: 98