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

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

Neuron 783 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.7063. Min Act: -0.1700

Data Index: 1211989 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.6750. Min Act: -0.1700

Data Index: 570049 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.6750. Min Act: -0.1700

Data Index: 1235439 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.6437. Min Act: -0.1700

Data Index: 763389 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5968. Min Act: -0.1700

Data Index: 706366 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.6281. Min Act: -0.1700

Data Index: 671140 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5811. Min Act: -0.1700

Data Index: 1273016 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5968. Min Act: -0.1700

Data Index: 947262 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.6124. Min Act: -0.1700

Data Index: 549295 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1049106 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5654. Min Act: -0.1700

Data Index: 255539 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5185. Min Act: -0.1700

Data Index: 691722 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5341. Min Act: -0.1700

Data Index: 1355532 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5341. Min Act: -0.1700

Data Index: 1174640 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5498. Min Act: -0.1700

Data Index: 137480 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5185. Min Act: -0.1700

Data Index: 888120 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5185. Min Act: -0.1700

Data Index: 312522 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.4558. Min Act: -0.1700

Data Index: 995261 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.4558. Min Act: -0.1700

Data Index: 995902 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 3.7063. Min Range: -3.7063

Max Act: 3.5028. Min Act: -0.1700

Data Index: 1022160 (C4 (Web Text))

Max Activating Token Index: 6