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

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

Neuron 118 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.4696. Min Act: -0.1700

Data Index: 1252312 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.3759. Min Act: -0.1700

Data Index: 1053354 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.3134. Min Act: -0.1700

Data Index: 1193208 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.3134. Min Act: -0.1700

Data Index: 1245754 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.3134. Min Act: -0.1700

Data Index: 1315068 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.3134. Min Act: -0.1700

Data Index: 683417 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2821. Min Act: -0.1700

Data Index: 906856 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2509. Min Act: -0.1700

Data Index: 682433 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2509. Min Act: -0.1700

Data Index: 437033 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2196. Min Act: -0.1700

Data Index: 1200632 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2196. Min Act: -0.1700

Data Index: 545287 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2196. Min Act: -0.1700

Data Index: 1312635 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2196. Min Act: -0.1700

Data Index: 808649 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.1884. Min Act: -0.1700

Data Index: 1076476 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2196. Min Act: -0.1700

Data Index: 1348740 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.1884. Min Act: -0.1700

Data Index: 796117 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2196. Min Act: -0.1700

Data Index: 422166 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.2509. Min Act: -0.1700

Data Index: 1199046 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.1884. Min Act: -0.1700

Data Index: 15369 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 5.4696. Min Range: -5.4696

Max Act: 5.1884. Min Act: -0.1700

Data Index: 1166295 (C4 (Web Text))

Max Activating Token Index: 459