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

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

Neuron 1591 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: 3.9697. Min Range: -3.9697

Max Act: 3.9697. Min Act: -0.1700

Data Index: 981130 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.9072. Min Act: -0.1700

Data Index: 1253936 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.8759. Min Act: -0.1700

Data Index: 637766 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.9072. Min Act: -0.1700

Data Index: 992902 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.8447. Min Act: -0.1700

Data Index: 671778 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.9072. Min Act: -0.1700

Data Index: 657487 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.8759. Min Act: -0.1700

Data Index: 970738 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.8134. Min Act: -0.1700

Data Index: 192570 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7821. Min Act: -0.1700

Data Index: 1069283 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7821. Min Act: -0.1700

Data Index: 118281 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.8134. Min Act: -0.1700

Data Index: 154150 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7821. Min Act: -0.1700

Data Index: 224067 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7821. Min Act: -0.1700

Data Index: 606484 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7508. Min Act: -0.1700

Data Index: 494607 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7821. Min Act: -0.1700

Data Index: 1140289 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7821. Min Act: -0.1700

Data Index: 1074608 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7195. Min Act: -0.1700

Data Index: 250091 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7821. Min Act: -0.1700

Data Index: 431449 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7195. Min Act: -0.1700

Data Index: 1013681 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 3.9697. Min Range: -3.9697

Max Act: 3.7508. Min Act: -0.1700

Data Index: 593283 (C4 (Web Text))

Max Activating Token Index: 625