Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1453 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.5556. Min Act: -0.1700

Data Index: 1031909 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.5086. Min Act: -0.1700

Data Index: 808759 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.5399. Min Act: -0.1700

Data Index: 225716 (C4 (Web Text))

Max Activating Token Index: 666

Text #3

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.5243. Min Act: -0.1700

Data Index: 1213495 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4929. Min Act: -0.1700

Data Index: 1227890 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4773. Min Act: -0.1700

Data Index: 924888 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4616. Min Act: -0.1700

Data Index: 110423 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4459. Min Act: -0.1700

Data Index: 265591 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4459. Min Act: -0.1700

Data Index: 816461 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4773. Min Act: -0.1700

Data Index: 1158443 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4146. Min Act: -0.1700

Data Index: 718942 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4616. Min Act: -0.1700

Data Index: 357246 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4459. Min Act: -0.1700

Data Index: 698764 (C4 (Web Text))

Max Activating Token Index: 563

Text #13

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4302. Min Act: -0.1700

Data Index: 397234 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4146. Min Act: -0.1700

Data Index: 1615107 (Python Code)

Max Activating Token Index: 355

Text #15

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.3675. Min Act: -0.1700

Data Index: 70850 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.3989. Min Act: -0.1700

Data Index: 378935 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4459. Min Act: -0.1700

Data Index: 19168 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.4146. Min Act: -0.1700

Data Index: 1102443 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 3.5556. Min Range: -3.5556

Max Act: 3.3518. Min Act: -0.1700

Data Index: 699596 (C4 (Web Text))

Max Activating Token Index: 642