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

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

Neuron 1458 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.5719. Min Act: -0.1700

Data Index: 955948 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.3844. Min Act: -0.1700

Data Index: 360371 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.3531. Min Act: -0.1700

Data Index: 1007870 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.3219. Min Act: -0.1700

Data Index: 1334159 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.3219. Min Act: -0.1700

Data Index: 20641 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2906. Min Act: -0.1700

Data Index: 98703 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.3531. Min Act: -0.1700

Data Index: 1094267 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2906. Min Act: -0.1700

Data Index: 108629 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.3219. Min Act: -0.1700

Data Index: 1046594 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2906. Min Act: -0.1700

Data Index: 353300 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2906. Min Act: -0.1700

Data Index: 257167 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2594. Min Act: -0.1700

Data Index: 813678 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2594. Min Act: -0.1700

Data Index: 958379 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2281. Min Act: -0.1700

Data Index: 324244 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2594. Min Act: -0.1700

Data Index: 63040 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2281. Min Act: -0.1700

Data Index: 346763 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2594. Min Act: -0.1700

Data Index: 758239 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2594. Min Act: -0.1700

Data Index: 215821 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2594. Min Act: -0.1700

Data Index: 1310451 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 5.5719. Min Range: -5.5719

Max Act: 5.2281. Min Act: -0.1700

Data Index: 7017 (C4 (Web Text))

Max Activating Token Index: 402