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

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

Neuron 1645 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: 3.3008. Min Range: -3.3008

Max Act: 3.3008. Min Act: -0.1700

Data Index: 247083 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.2694. Min Act: -0.1700

Data Index: 1013891 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.2379. Min Act: -0.1700

Data Index: 1069336 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.2851. Min Act: -0.1700

Data Index: 272416 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.2222. Min Act: -0.1700

Data Index: 936918 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.2379. Min Act: -0.1700

Data Index: 43135 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1908. Min Act: -0.1700

Data Index: 1142431 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1750. Min Act: -0.1700

Data Index: 630518 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1750. Min Act: -0.1700

Data Index: 957052 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1750. Min Act: -0.1700

Data Index: 235807 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1435. Min Act: -0.1700

Data Index: 428782 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1278. Min Act: -0.1700

Data Index: 1111530 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1278. Min Act: -0.1700

Data Index: 584766 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1120. Min Act: -0.1700

Data Index: 500541 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1120. Min Act: -0.1700

Data Index: 620084 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.0805. Min Act: -0.1700

Data Index: 937415 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.1120. Min Act: -0.1700

Data Index: 279250 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.0962. Min Act: -0.1700

Data Index: 532524 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.0805. Min Act: -0.1700

Data Index: 1049790 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 3.3008. Min Range: -3.3008

Max Act: 3.0647. Min Act: -0.1700

Data Index: 605702 (C4 (Web Text))

Max Activating Token Index: 305