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

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

Neuron 1867 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: 3.9883. Min Range: -3.9883

Max Act: 3.9883. Min Act: -0.1700

Data Index: 848374 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8632. Min Act: -0.1700

Data Index: 912313 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8319. Min Act: -0.1700

Data Index: 569424 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8006. Min Act: -0.1700

Data Index: 25115 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8006. Min Act: -0.1700

Data Index: 598482 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8319. Min Act: -0.1700

Data Index: 436071 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8006. Min Act: -0.1700

Data Index: 271728 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7693. Min Act: -0.1700

Data Index: 1285390 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7693. Min Act: -0.1700

Data Index: 473732 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7693. Min Act: -0.1700

Data Index: 133571 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7693. Min Act: -0.1700

Data Index: 1344499 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7693. Min Act: -0.1700

Data Index: 1293120 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7693. Min Act: -0.1700

Data Index: 556077 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7381. Min Act: -0.1700

Data Index: 851807 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.8006. Min Act: -0.1700

Data Index: 1000031 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7693. Min Act: -0.1700

Data Index: 500378 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7068. Min Act: -0.1700

Data Index: 249464 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7068. Min Act: -0.1700

Data Index: 993715 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.7381. Min Act: -0.1700

Data Index: 31541 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 3.9883. Min Range: -3.9883

Max Act: 3.6442. Min Act: -0.1700

Data Index: 671396 (C4 (Web Text))

Max Activating Token Index: 581