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

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

Neuron 188 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.8003. Min Act: -0.1700

Data Index: 838679 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.6438. Min Act: -0.1700

Data Index: 120650 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5969. Min Act: -0.1700

Data Index: 1350910 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.6438. Min Act: -0.1700

Data Index: 828537 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5969. Min Act: -0.1700

Data Index: 694082 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5969. Min Act: -0.1700

Data Index: 412683 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.6125. Min Act: -0.1700

Data Index: 176902 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5969. Min Act: -0.1700

Data Index: 634585 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5812. Min Act: -0.1700

Data Index: 857857 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5656. Min Act: -0.1700

Data Index: 824973 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5812. Min Act: -0.1700

Data Index: 553303 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5812. Min Act: -0.1700

Data Index: 1043409 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5656. Min Act: -0.1700

Data Index: 540910 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5186. Min Act: -0.1700

Data Index: 601116 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5656. Min Act: -0.1700

Data Index: 964303 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5342. Min Act: -0.1700

Data Index: 794260 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5342. Min Act: -0.1700

Data Index: 1281028 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5342. Min Act: -0.1700

Data Index: 629435 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.5812. Min Act: -0.1700

Data Index: 250166 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 3.8003. Min Range: -3.8003

Max Act: 3.4716. Min Act: -0.1700

Data Index: 814202 (C4 (Web Text))

Max Activating Token Index: 475