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

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

Neuron 1146 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: 3.2538. Min Range: -3.2538

Max Act: 3.2538. Min Act: -0.1700

Data Index: 713370 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.2381. Min Act: -0.1700

Data Index: 1098173 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1909. Min Act: -0.1700

Data Index: 518009 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.2067. Min Act: -0.1700

Data Index: 766927 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1752. Min Act: -0.1700

Data Index: 458646 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1752. Min Act: -0.1700

Data Index: 1177439 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1752. Min Act: -0.1700

Data Index: 619778 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1594. Min Act: -0.1700

Data Index: 274779 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1437. Min Act: -0.1700

Data Index: 714086 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1437. Min Act: -0.1700

Data Index: 1026273 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1122. Min Act: -0.1700

Data Index: 715889 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1122. Min Act: -0.1700

Data Index: 183496 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1122. Min Act: -0.1700

Data Index: 1013406 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1122. Min Act: -0.1700

Data Index: 1120591 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1122. Min Act: -0.1700

Data Index: 310366 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1122. Min Act: -0.1700

Data Index: 212476 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1122. Min Act: -0.1700

Data Index: 796691 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.0964. Min Act: -0.1700

Data Index: 793034 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.0964. Min Act: -0.1700

Data Index: 1305150 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 3.2538. Min Range: -3.2538

Max Act: 3.1122. Min Act: -0.1700

Data Index: 435959 (C4 (Web Text))

Max Activating Token Index: 56