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

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

Neuron 146 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.6815. Min Act: -0.1700

Data Index: 1102407 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.6189. Min Act: -0.1700

Data Index: 236529 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.6189. Min Act: -0.1700

Data Index: 955969 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.6189. Min Act: -0.1700

Data Index: 898069 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.6189. Min Act: -0.1700

Data Index: 866580 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5876. Min Act: -0.1700

Data Index: 910406 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5876. Min Act: -0.1700

Data Index: 911794 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5562. Min Act: -0.1700

Data Index: 474975 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5876. Min Act: -0.1700

Data Index: 494999 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5562. Min Act: -0.1700

Data Index: 526139 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5562. Min Act: -0.1700

Data Index: 678104 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5562. Min Act: -0.1700

Data Index: 1185653 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5562. Min Act: -0.1700

Data Index: 31370 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5562. Min Act: -0.1700

Data Index: 26548 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5562. Min Act: -0.1700

Data Index: 1158762 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5562. Min Act: -0.1700

Data Index: 572707 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5249. Min Act: -0.1700

Data Index: 1032815 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5249. Min Act: -0.1700

Data Index: 842985 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.4936. Min Act: -0.1700

Data Index: 435752 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 3.6815. Min Range: -3.6815

Max Act: 3.5249. Min Act: -0.1700

Data Index: 947392 (C4 (Web Text))

Max Activating Token Index: 3