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

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

Neuron 774 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: 5.4468. Min Range: -5.4468

Max Act: 5.4468. Min Act: -0.1700

Data Index: 1338396 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.1968. Min Act: -0.1700

Data Index: 1292638 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.1343. Min Act: -0.1700

Data Index: 8658 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.1343. Min Act: -0.1700

Data Index: 987246 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0718. Min Act: -0.1700

Data Index: 117529 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.1030. Min Act: -0.1700

Data Index: 1299663 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0718. Min Act: -0.1700

Data Index: 1288107 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 5.4468. Min Range: -5.4468

Max Act: 4.9780. Min Act: -0.1700

Data Index: 1305037 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0405. Min Act: -0.1700

Data Index: 1103421 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0093. Min Act: -0.1700

Data Index: 781461 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0718. Min Act: -0.1700

Data Index: 1238910 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0405. Min Act: -0.1700

Data Index: 1090016 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0093. Min Act: -0.1700

Data Index: 534405 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0405. Min Act: -0.1700

Data Index: 676547 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0093. Min Act: -0.1700

Data Index: 229468 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0405. Min Act: -0.1700

Data Index: 1268340 (C4 (Web Text))

Max Activating Token Index: 647

Text #16

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0093. Min Act: -0.1700

Data Index: 1230713 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 5.4468. Min Range: -5.4468

Max Act: 4.9780. Min Act: -0.1700

Data Index: 953252 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 5.4468. Min Range: -5.4468

Max Act: 5.0093. Min Act: -0.1700

Data Index: 593302 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 5.4468. Min Range: -5.4468

Max Act: 4.9780. Min Act: -0.1700

Data Index: 25256 (C4 (Web Text))

Max Activating Token Index: 290