Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1133 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.7450. Min Act: -0.1700

Data Index: 374455 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6824. Min Act: -0.1700

Data Index: 815857 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6824. Min Act: -0.1700

Data Index: 1104784 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6667. Min Act: -0.1700

Data Index: 426206 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6667. Min Act: -0.1700

Data Index: 1181673 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6667. Min Act: -0.1700

Data Index: 320101 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6511. Min Act: -0.1700

Data Index: 543342 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6354. Min Act: -0.1700

Data Index: 150731 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6354. Min Act: -0.1700

Data Index: 72202 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6041. Min Act: -0.1700

Data Index: 1009339 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6198. Min Act: -0.1700

Data Index: 1038135 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6198. Min Act: -0.1700

Data Index: 1115031 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6354. Min Act: -0.1700

Data Index: 584584 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6198. Min Act: -0.1700

Data Index: 616748 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6198. Min Act: -0.1700

Data Index: 3262 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6198. Min Act: -0.1700

Data Index: 905720 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6354. Min Act: -0.1700

Data Index: 208193 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.5884. Min Act: -0.1700

Data Index: 912506 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6041. Min Act: -0.1700

Data Index: 620984 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 3.7450. Min Range: -3.7450

Max Act: 3.6041. Min Act: -0.1700

Data Index: 104924 (C4 (Web Text))

Max Activating Token Index: 805