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

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

Neuron 1833 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.7067. Min Act: -0.1700

Data Index: 414986 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5972. Min Act: -0.1700

Data Index: 1003331 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.6128. Min Act: -0.1700

Data Index: 787326 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.6128. Min Act: -0.1700

Data Index: 196494 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5658. Min Act: -0.1700

Data Index: 1190380 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5502. Min Act: -0.1700

Data Index: 437137 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5345. Min Act: -0.1700

Data Index: 1126785 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5502. Min Act: -0.1700

Data Index: 528760 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5032. Min Act: -0.1700

Data Index: 609948 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.5189. Min Act: -0.1700

Data Index: 292529 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4562. Min Act: -0.1700

Data Index: 1279411 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4405. Min Act: -0.1700

Data Index: 234638 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4562. Min Act: -0.1700

Data Index: 111666 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4562. Min Act: -0.1700

Data Index: 352835 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4562. Min Act: -0.1700

Data Index: 512985 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4875. Min Act: -0.1700

Data Index: 620345 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4405. Min Act: -0.1700

Data Index: 973362 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4718. Min Act: -0.1700

Data Index: 709837 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.3935. Min Act: -0.1700

Data Index: 971019 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 3.7067. Min Range: -3.7067

Max Act: 3.4248. Min Act: -0.1700

Data Index: 462183 (C4 (Web Text))

Max Activating Token Index: 685