Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1132 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.5624. Min Act: -0.1700

Data Index: 1225379 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.3749. Min Act: -0.1700

Data Index: 1272304 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.3592. Min Act: -0.1700

Data Index: 853872 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.2655. Min Act: -0.1700

Data Index: 721104 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.2655. Min Act: -0.1700

Data Index: 735893 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.2967. Min Act: -0.1700

Data Index: 578036 (C4 (Web Text))

Max Activating Token Index: 672

Text #6

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.2655. Min Act: -0.1700

Data Index: 818959 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.2499. Min Act: -0.1700

Data Index: 1093152 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.2655. Min Act: -0.1700

Data Index: 267007 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.2186. Min Act: -0.1700

Data Index: 1190037 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.2499. Min Act: -0.1700

Data Index: 974383 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.2655. Min Act: -0.1700

Data Index: 844498 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.1405. Min Act: -0.1700

Data Index: 201214 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.1405. Min Act: -0.1700

Data Index: 110955 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.1405. Min Act: -0.1700

Data Index: 742704 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.1561. Min Act: -0.1700

Data Index: 87062 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.1717. Min Act: -0.1700

Data Index: 829199 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.1405. Min Act: -0.1700

Data Index: 548623 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.1717. Min Act: -0.1700

Data Index: 1180801 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 5.5624. Min Range: -5.5624

Max Act: 5.1405. Min Act: -0.1700

Data Index: 742057 (C4 (Web Text))

Max Activating Token Index: 670