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

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

Neuron 190 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: 5.9060. Min Range: -5.9060

Max Act: 5.9060. Min Act: -0.1700

Data Index: 546620 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.7185. Min Act: -0.1700

Data Index: 1096060 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.7185. Min Act: -0.1700

Data Index: 1048724 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.6872. Min Act: -0.1700

Data Index: 429298 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.6560. Min Act: -0.1700

Data Index: 902776 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.6247. Min Act: -0.1700

Data Index: 1136106 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.5935. Min Act: -0.1700

Data Index: 1128371 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.6247. Min Act: -0.1700

Data Index: 91469 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.5935. Min Act: -0.1700

Data Index: 10329 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.5310. Min Act: -0.1700

Data Index: 1324320 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.5622. Min Act: -0.1700

Data Index: 995547 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.4685. Min Act: -0.1700

Data Index: 576169 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.5310. Min Act: -0.1700

Data Index: 1043012 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.4685. Min Act: -0.1700

Data Index: 1069926 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.4372. Min Act: -0.1700

Data Index: 1145714 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.4060. Min Act: -0.1700

Data Index: 1104488 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.4685. Min Act: -0.1700

Data Index: 1115470 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.4060. Min Act: -0.1700

Data Index: 523214 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.4372. Min Act: -0.1700

Data Index: 403947 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 5.9060. Min Range: -5.9060

Max Act: 5.3435. Min Act: -0.1700

Data Index: 15869 (C4 (Web Text))

Max Activating Token Index: 577