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

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

Neuron 543 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: 3.4556. Min Range: -3.4556

Max Act: 3.4086. Min Act: -0.1700

Data Index: 259830 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.4556. Min Act: -0.1700

Data Index: 873128 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.4243. Min Act: -0.1700

Data Index: 745019 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3929. Min Act: -0.1700

Data Index: 233792 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3615. Min Act: -0.1700

Data Index: 288314 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3772. Min Act: -0.1700

Data Index: 132266 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3615. Min Act: -0.1700

Data Index: 115991 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3145. Min Act: -0.1700

Data Index: 570080 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3145. Min Act: -0.1700

Data Index: 247190 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3302. Min Act: -0.1700

Data Index: 163901 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3302. Min Act: -0.1700

Data Index: 1020248 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3302. Min Act: -0.1700

Data Index: 300305 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3459. Min Act: -0.1700

Data Index: 1066620 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3145. Min Act: -0.1700

Data Index: 1021579 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.2830. Min Act: -0.1700

Data Index: 576330 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.2830. Min Act: -0.1700

Data Index: 1087928 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.2988. Min Act: -0.1700

Data Index: 219839 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.2988. Min Act: -0.1700

Data Index: 645828 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.2988. Min Act: -0.1700

Data Index: 747326 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 3.4556. Min Range: -3.4556

Max Act: 3.3145. Min Act: -0.1700

Data Index: 180676 (C4 (Web Text))

Max Activating Token Index: 709