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

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

Neuron 1136 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.8088. Min Act: -0.1700

Data Index: 661971 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7932. Min Act: -0.1700

Data Index: 1341463 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7619. Min Act: -0.1700

Data Index: 818294 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7306. Min Act: -0.1700

Data Index: 54946 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7306. Min Act: -0.1700

Data Index: 1205782 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7462. Min Act: -0.1700

Data Index: 205914 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7462. Min Act: -0.1700

Data Index: 321098 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7149. Min Act: -0.1700

Data Index: 730734 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7306. Min Act: -0.1700

Data Index: 42155 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7306. Min Act: -0.1700

Data Index: 215759 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7306. Min Act: -0.1700

Data Index: 906656 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7306. Min Act: -0.1700

Data Index: 1227232 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7149. Min Act: -0.1700

Data Index: 1125286 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7149. Min Act: -0.1700

Data Index: 468437 (C4 (Web Text))

Max Activating Token Index: 786

Text #14

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7149. Min Act: -0.1700

Data Index: 706557 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.7149. Min Act: -0.1700

Data Index: 495315 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.6993. Min Act: -0.1700

Data Index: 647291 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.6836. Min Act: -0.1700

Data Index: 778376 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.6993. Min Act: -0.1700

Data Index: 710895 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 3.8088. Min Range: -3.8088

Max Act: 3.6993. Min Act: -0.1700

Data Index: 914349 (C4 (Web Text))

Max Activating Token Index: 1020