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

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

Neuron 1830 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: 3.3992. Min Range: -3.3992

Max Act: 3.3678. Min Act: -0.1700

Data Index: 160654 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.3678. Min Act: -0.1700

Data Index: 760158 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.3992. Min Act: -0.1700

Data Index: 924062 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2736. Min Act: -0.1700

Data Index: 455855 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1793. Min Act: -0.1700

Data Index: 1442660 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2422. Min Act: -0.1700

Data Index: 733682 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2107. Min Act: -0.1700

Data Index: 358895 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2422. Min Act: -0.1700

Data Index: 775274 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2107. Min Act: -0.1700

Data Index: 729640 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2107. Min Act: -0.1700

Data Index: 596919 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2107. Min Act: -0.1700

Data Index: 801781 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1793. Min Act: -0.1700

Data Index: 288678 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2107. Min Act: -0.1700

Data Index: 398671 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.2107. Min Act: -0.1700

Data Index: 1264445 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1793. Min Act: -0.1700

Data Index: 572793 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1478. Min Act: -0.1700

Data Index: 980409 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1793. Min Act: -0.1700

Data Index: 509053 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1793. Min Act: -0.1700

Data Index: 1238562 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1793. Min Act: -0.1700

Data Index: 786097 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 3.3992. Min Range: -3.3992

Max Act: 3.1478. Min Act: -0.1700

Data Index: 1702 (C4 (Web Text))

Max Activating Token Index: 840