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

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

Neuron 1153 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: 5.2926. Min Range: -5.2926

Max Act: 5.2926. Min Act: -0.1700

Data Index: 799813 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 5.2926. Min Range: -5.2926

Max Act: 5.2301. Min Act: -0.1700

Data Index: 1014991 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.8551. Min Act: -0.1700

Data Index: 525042 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.7613. Min Act: -0.1700

Data Index: 81277 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.7301. Min Act: -0.1700

Data Index: 1191007 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.7301. Min Act: -0.1700

Data Index: 474358 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.6988. Min Act: -0.1700

Data Index: 700981 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.6676. Min Act: -0.1700

Data Index: 32153 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.6051. Min Act: -0.1700

Data Index: 563081 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.6051. Min Act: -0.1700

Data Index: 567327 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.6676. Min Act: -0.1700

Data Index: 578462 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.6676. Min Act: -0.1700

Data Index: 492038 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.6363. Min Act: -0.1700

Data Index: 803760 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.6051. Min Act: -0.1700

Data Index: 18064 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.5426. Min Act: -0.1700

Data Index: 572061 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.5738. Min Act: -0.1700

Data Index: 1192983 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.5426. Min Act: -0.1700

Data Index: 691878 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.5426. Min Act: -0.1700

Data Index: 706721 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.5426. Min Act: -0.1700

Data Index: 795613 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 5.2926. Min Range: -5.2926

Max Act: 4.5426. Min Act: -0.1700

Data Index: 659463 (C4 (Web Text))

Max Activating Token Index: 844