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

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

Neuron 1910 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: 3.2951. Min Range: -3.2951

Max Act: 3.2951. Min Act: -0.1700

Data Index: 831427 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.2008. Min Act: -0.1700

Data Index: 1093805 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1017492 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0747. Min Act: -0.1700

Data Index: 778168 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0905. Min Act: -0.1700

Data Index: 924000 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.1063. Min Act: -0.1700

Data Index: 1298209 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0905. Min Act: -0.1700

Data Index: 1288003 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0747. Min Act: -0.1700

Data Index: 1304599 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0747. Min Act: -0.1700

Data Index: 482505 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0589. Min Act: -0.1700

Data Index: 210523 (C4 (Web Text))

Max Activating Token Index: 504

Text #10

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0432. Min Act: -0.1700

Data Index: 375986 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0432. Min Act: -0.1700

Data Index: 589811 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0589. Min Act: -0.1700

Data Index: 746175 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0274. Min Act: -0.1700

Data Index: 276686 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0274. Min Act: -0.1700

Data Index: 258706 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0274. Min Act: -0.1700

Data Index: 401486 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0116. Min Act: -0.1700

Data Index: 229953 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0274. Min Act: -0.1700

Data Index: 412176 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0116. Min Act: -0.1700

Data Index: 522985 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 3.2951. Min Range: -3.2951

Max Act: 3.0116. Min Act: -0.1700

Data Index: 389269 (C4 (Web Text))

Max Activating Token Index: 80