Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1606 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2126. Min Range: -5.2126

Max Act: 5.2126. Min Act: -0.1700

Data Index: 570308 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 5.2126. Min Range: -5.2126

Max Act: 5.1501. Min Act: -0.1700

Data Index: 997977 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 5.2126. Min Range: -5.2126

Max Act: 5.1501. Min Act: -0.1700

Data Index: 1042044 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 5.2126. Min Range: -5.2126

Max Act: 5.1188. Min Act: -0.1700

Data Index: 83003 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 5.2126. Min Range: -5.2126

Max Act: 5.0876. Min Act: -0.1700

Data Index: 323414 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 5.2126. Min Range: -5.2126

Max Act: 5.0563. Min Act: -0.1700

Data Index: 819920 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9626. Min Act: -0.1700

Data Index: 530640 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9938. Min Act: -0.1700

Data Index: 1240362 (C4 (Web Text))

Max Activating Token Index: 563

Text #8

Max Range: 5.2126. Min Range: -5.2126

Max Act: 5.0563. Min Act: -0.1700

Data Index: 1195345 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.9001. Min Act: -0.1700

Data Index: 1281383 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.8063. Min Act: -0.1700

Data Index: 707162 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.8688. Min Act: -0.1700

Data Index: 225202 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.8063. Min Act: -0.1700

Data Index: 422498 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.8063. Min Act: -0.1700

Data Index: 438117 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.8376. Min Act: -0.1700

Data Index: 1084622 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.7751. Min Act: -0.1700

Data Index: 272009 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.7438. Min Act: -0.1700

Data Index: 1330965 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.6501. Min Act: -0.1700

Data Index: 572858 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.5875. Min Act: -0.1700

Data Index: 627297 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 5.2126. Min Range: -5.2126

Max Act: 4.5875. Min Act: -0.1700

Data Index: 674264 (C4 (Web Text))

Max Activating Token Index: 74