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

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

Neuron 341 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: 5.5642. Min Range: -5.5642

Max Act: 5.5642. Min Act: -0.1700

Data Index: 95046 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.4392. Min Act: -0.1700

Data Index: 1016642 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.4080. Min Act: -0.1699

Data Index: 236864 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.3142. Min Act: -0.1700

Data Index: 705921 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.3142. Min Act: -0.1700

Data Index: 595703 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.3455. Min Act: -0.1700

Data Index: 1240610 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.2205. Min Act: -0.1700

Data Index: 1282080 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.3455. Min Act: -0.1700

Data Index: 1009457 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.2830. Min Act: -0.1700

Data Index: 191957 (C4 (Web Text))

Max Activating Token Index: 903

Text #9

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.2830. Min Act: -0.1700

Data Index: 1144923 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.2205. Min Act: -0.1700

Data Index: 267262 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.3142. Min Act: -0.1700

Data Index: 657718 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.2517. Min Act: -0.1700

Data Index: 948039 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.2517. Min Act: -0.1700

Data Index: 1321743 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.2830. Min Act: -0.1700

Data Index: 1181748 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.2205. Min Act: -0.1700

Data Index: 1249797 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.2205. Min Act: -0.1700

Data Index: 688650 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.1267. Min Act: -0.1700

Data Index: 590015 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.1892. Min Act: -0.1700

Data Index: 350658 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 5.5642. Min Range: -5.5642

Max Act: 5.1267. Min Act: -0.1700

Data Index: 830278 (C4 (Web Text))

Max Activating Token Index: 395