Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1721 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.2840. Min Act: -0.1700

Data Index: 857482 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1582. Min Act: -0.1700

Data Index: 832487 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1739. Min Act: -0.1700

Data Index: 380084 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1267. Min Act: -0.1700

Data Index: 153643 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1109. Min Act: -0.1700

Data Index: 1244256 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1109. Min Act: -0.1700

Data Index: 1106101 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1109. Min Act: -0.1700

Data Index: 474488 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.1109. Min Act: -0.1700

Data Index: 284761 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0952. Min Act: -0.1700

Data Index: 446034 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0478. Min Act: -0.1700

Data Index: 737319 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0794. Min Act: -0.1700

Data Index: 926837 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0794. Min Act: -0.1700

Data Index: 964631 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0636. Min Act: -0.1700

Data Index: 974014 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0636. Min Act: -0.1700

Data Index: 1279276 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0478. Min Act: -0.1700

Data Index: 1296435 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0320. Min Act: -0.1700

Data Index: 331886 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0636. Min Act: -0.1700

Data Index: 1276562 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0636. Min Act: -0.1700

Data Index: 653034 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0478. Min Act: -0.1700

Data Index: 694336 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 3.2840. Min Range: -3.2840

Max Act: 3.0320. Min Act: -0.1700

Data Index: 911978 (C4 (Web Text))

Max Activating Token Index: 262