Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2009 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4517. Min Act: -0.1700

Data Index: 521510 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.5144. Min Act: -0.1700

Data Index: 607383 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4987. Min Act: -0.1700

Data Index: 1273892 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4517. Min Act: -0.1700

Data Index: 334116 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4360. Min Act: -0.1700

Data Index: 543387 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4673. Min Act: -0.1700

Data Index: 969209 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4517. Min Act: -0.1700

Data Index: 1049403 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4360. Min Act: -0.1700

Data Index: 228597 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4360. Min Act: -0.1700

Data Index: 973700 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4517. Min Act: -0.1700

Data Index: 318186 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4360. Min Act: -0.1700

Data Index: 1254536 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4517. Min Act: -0.1700

Data Index: 88973 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4203. Min Act: -0.1700

Data Index: 1328157 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3733. Min Act: -0.1700

Data Index: 310030 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.4360. Min Act: -0.1700

Data Index: 297131 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3889. Min Act: -0.1700

Data Index: 248645 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3889. Min Act: -0.1700

Data Index: 1222915 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3889. Min Act: -0.1700

Data Index: 753498 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3576. Min Act: -0.1700

Data Index: 651604 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 3.5144. Min Range: -3.5144

Max Act: 3.3889. Min Act: -0.1700

Data Index: 345416 (C4 (Web Text))

Max Activating Token Index: 479