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

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

Neuron 1886 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.3973. Min Act: -0.1700

Data Index: 1512169 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.3973. Min Act: -0.1700

Data Index: 1371192 (Python Code)

Max Activating Token Index: 217

Text #2

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.3348. Min Act: -0.1700

Data Index: 1432832 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.2723. Min Act: -0.1700

Data Index: 1530143 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.3348. Min Act: -0.1700

Data Index: 1605766 (Python Code)

Max Activating Token Index: 897

Text #5

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.2723. Min Act: -0.1700

Data Index: 271771 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.2723. Min Act: -0.1700

Data Index: 1434776 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.3348. Min Act: -0.1700

Data Index: 1543063 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.2723. Min Act: -0.1700

Data Index: 1534621 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.2098. Min Act: -0.1700

Data Index: 1518123 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.1473. Min Act: -0.1700

Data Index: 233877 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.2098. Min Act: -0.1700

Data Index: 1489415 (Python Code)

Max Activating Token Index: 550

Text #12

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.2098. Min Act: -0.1700

Data Index: 1446480 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.0848. Min Act: -0.1700

Data Index: 1591504 (Python Code)

Max Activating Token Index: 874

Text #14

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.1473. Min Act: -0.1700

Data Index: 1603496 (Python Code)

Max Activating Token Index: 830

Text #15

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.1473. Min Act: -0.1700

Data Index: 1374916 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.1473. Min Act: -0.1700

Data Index: 1631735 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.1473. Min Act: -0.1700

Data Index: 1650725 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.1473. Min Act: -0.1700

Data Index: 1569285 (Python Code)

Max Activating Token Index: 665

Text #19

Max Range: 5.3973. Min Range: -5.3973

Max Act: 5.2098. Min Act: -0.1700

Data Index: 1595441 (Python Code)

Max Activating Token Index: 832