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

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

Neuron 1902 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: 5.6849. Min Range: -5.6849

Max Act: 5.6224. Min Act: -0.1700

Data Index: 1335479 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.6849. Min Act: -0.1700

Data Index: 104148 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.6849. Min Act: -0.1700

Data Index: 432384 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.5911. Min Act: -0.1700

Data Index: 1063432 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.5911. Min Act: -0.1700

Data Index: 1174662 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.5599. Min Act: -0.1700

Data Index: 619788 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.5911. Min Act: -0.1700

Data Index: 1211944 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.5286. Min Act: -0.1700

Data Index: 259036 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.5286. Min Act: -0.1700

Data Index: 526028 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4974. Min Act: -0.1700

Data Index: 5187 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4974. Min Act: -0.1700

Data Index: 132315 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4661. Min Act: -0.1700

Data Index: 358450 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4661. Min Act: -0.1700

Data Index: 954411 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4349. Min Act: -0.1700

Data Index: 1158924 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4974. Min Act: -0.1700

Data Index: 1322311 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4974. Min Act: -0.1700

Data Index: 747697 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4349. Min Act: -0.1700

Data Index: 934395 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4036. Min Act: -0.1700

Data Index: 627092 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4349. Min Act: -0.1700

Data Index: 1073861 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 5.6849. Min Range: -5.6849

Max Act: 5.4349. Min Act: -0.1700

Data Index: 555575 (C4 (Web Text))

Max Activating Token Index: 749