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

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

Neuron 945 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1092. Min Range: -5.1092

Max Act: 5.1092. Min Act: -0.1700

Data Index: 1282756 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 5.1092. Min Range: -5.1092

Max Act: 5.0155. Min Act: -0.1700

Data Index: 437913 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 5.1092. Min Range: -5.1092

Max Act: 5.0780. Min Act: -0.1700

Data Index: 517805 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.9217. Min Act: -0.1700

Data Index: 934573 (C4 (Web Text))

Max Activating Token Index: 380

Text #4

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7967. Min Act: -0.1700

Data Index: 712399 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.8592. Min Act: -0.1700

Data Index: 43667 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7967. Min Act: -0.1700

Data Index: 43252 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7967. Min Act: -0.1700

Data Index: 578634 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7342. Min Act: -0.1700

Data Index: 464338 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7030. Min Act: -0.1700

Data Index: 369563 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7030. Min Act: -0.1700

Data Index: 557985 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7030. Min Act: -0.1700

Data Index: 958967 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7030. Min Act: -0.1700

Data Index: 913624 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.6717. Min Act: -0.1700

Data Index: 871913 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.6717. Min Act: -0.1700

Data Index: 827339 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.6717. Min Act: -0.1700

Data Index: 515961 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.6717. Min Act: -0.1700

Data Index: 762847 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7030. Min Act: -0.1700

Data Index: 1227113 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7342. Min Act: -0.1700

Data Index: 1153352 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 5.1092. Min Range: -5.1092

Max Act: 4.7030. Min Act: -0.1700

Data Index: 161447 (C4 (Web Text))

Max Activating Token Index: 55