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

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

Neuron 1745 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.6234. Min Act: -0.1700

Data Index: 1602527 (Python Code)

Max Activating Token Index: 996

Text #1

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.6234. Min Act: -0.1700

Data Index: 1353204 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.5608. Min Act: -0.1700

Data Index: 1420268 (Python Code)

Max Activating Token Index: 698

Text #3

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.5608. Min Act: -0.1700

Data Index: 171348 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.5608. Min Act: -0.1700

Data Index: 1635008 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4981. Min Act: -0.1700

Data Index: 1494459 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4668. Min Act: -0.1700

Data Index: 1447138 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.5138. Min Act: -0.1700

Data Index: 498442 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4824. Min Act: -0.1700

Data Index: 567554 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4981. Min Act: -0.1700

Data Index: 1014085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4981. Min Act: -0.1700

Data Index: 1529511 (Python Code)

Max Activating Token Index: 804

Text #11

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4981. Min Act: -0.1700

Data Index: 410847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4981. Min Act: -0.1700

Data Index: 148915 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4824. Min Act: -0.1700

Data Index: 1521350 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4824. Min Act: -0.1700

Data Index: 1650957 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4668. Min Act: -0.1700

Data Index: 94392 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4354. Min Act: -0.1700

Data Index: 1382922 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4668. Min Act: -0.1700

Data Index: 932644 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4668. Min Act: -0.1700

Data Index: 84347 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4354. Min Act: -0.1700

Data Index: 1558712 (Python Code)

Max Activating Token Index: 483