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

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

Neuron 1187 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: 3.6793. Min Range: -3.6793

Max Act: 3.6793. Min Act: -0.1700

Data Index: 1027008 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.5540. Min Act: -0.1700

Data Index: 1423216 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.5227. Min Act: -0.1700

Data Index: 426777 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.5540. Min Act: -0.1700

Data Index: 1214360 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.5227. Min Act: -0.1700

Data Index: 354001 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.5227. Min Act: -0.1700

Data Index: 710721 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.4600. Min Act: -0.1700

Data Index: 931469 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.4287. Min Act: -0.1700

Data Index: 908393 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3659. Min Act: -0.1700

Data Index: 1348073 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3973. Min Act: -0.1700

Data Index: 579273 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3973. Min Act: -0.1700

Data Index: 324218 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3659. Min Act: -0.1700

Data Index: 883147 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3973. Min Act: -0.1700

Data Index: 552100 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3345. Min Act: -0.1700

Data Index: 909943 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3659. Min Act: -0.1700

Data Index: 1036710 (C4 (Web Text))

Max Activating Token Index: 330

Text #15

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3659. Min Act: -0.1700

Data Index: 758107 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3345. Min Act: -0.1700

Data Index: 170357 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3659. Min Act: -0.1700

Data Index: 708830 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3659. Min Act: -0.1700

Data Index: 182830 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 3.6793. Min Range: -3.6793

Max Act: 3.3973. Min Act: -0.1700

Data Index: 501084 (C4 (Web Text))

Max Activating Token Index: 350