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

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

Neuron 931 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: 7.0119. Min Range: -7.0119

Max Act: 7.0119. Min Act: -0.1700

Data Index: 43894 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.9806. Min Act: -0.1700

Data Index: 1295185 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.8244. Min Act: -0.1700

Data Index: 662045 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.8244. Min Act: -0.1700

Data Index: 402131 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.5119. Min Act: -0.1700

Data Index: 1433363 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.5431. Min Act: -0.1700

Data Index: 1050429 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.5744. Min Act: -0.1700

Data Index: 845012 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.4494. Min Act: -0.1700

Data Index: 1139872 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.5119. Min Act: -0.1700

Data Index: 788334 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.4181. Min Act: -0.1700

Data Index: 285549 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.4494. Min Act: -0.1700

Data Index: 33198 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.4181. Min Act: -0.1700

Data Index: 150954 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.5119. Min Act: -0.1700

Data Index: 984521 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.4181. Min Act: -0.1700

Data Index: 1348151 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.4494. Min Act: -0.1700

Data Index: 1011959 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.4494. Min Act: -0.1700

Data Index: 1278681 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.3556. Min Act: -0.1700

Data Index: 332121 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.3244. Min Act: -0.1700

Data Index: 784285 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.3556. Min Act: -0.1700

Data Index: 1027626 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 7.0119. Min Range: -7.0119

Max Act: 6.4181. Min Act: -0.1700

Data Index: 164576 (C4 (Web Text))

Max Activating Token Index: 357