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

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

Neuron 531 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: 5.9718. Min Range: -5.9718

Max Act: 5.9718. Min Act: -0.1700

Data Index: 157727 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.5655. Min Act: -0.1700

Data Index: 1245181 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.4718. Min Act: -0.1700

Data Index: 179522 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.4718. Min Act: -0.1700

Data Index: 208423 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.4718. Min Act: -0.1700

Data Index: 945629 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.4405. Min Act: -0.1700

Data Index: 1181538 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.4093. Min Act: -0.1700

Data Index: 149255 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.4405. Min Act: -0.1700

Data Index: 1356449 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.3468. Min Act: -0.1700

Data Index: 44788 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.4405. Min Act: -0.1700

Data Index: 398900 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.3155. Min Act: -0.1700

Data Index: 1064010 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.4093. Min Act: -0.1700

Data Index: 1055495 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.3155. Min Act: -0.1700

Data Index: 1164742 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.3780. Min Act: -0.1700

Data Index: 174512 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.2218. Min Act: -0.1700

Data Index: 1302076 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.3155. Min Act: -0.1700

Data Index: 476677 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.3155. Min Act: -0.1700

Data Index: 945113 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.3468. Min Act: -0.1700

Data Index: 1299549 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.3155. Min Act: -0.1700

Data Index: 708093 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 5.9718. Min Range: -5.9718

Max Act: 5.3155. Min Act: -0.1700

Data Index: 52056 (C4 (Web Text))

Max Activating Token Index: 685