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

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

Neuron 1535 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.1661. Min Act: -0.1700

Data Index: 736548 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.1031. Min Act: -0.1700

Data Index: 513604 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0873. Min Act: -0.1700

Data Index: 170553 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0873. Min Act: -0.1700

Data Index: 1310249 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0715. Min Act: -0.1700

Data Index: 955263 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0715. Min Act: -0.1700

Data Index: 821366 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0715. Min Act: -0.1700

Data Index: 913610 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0715. Min Act: -0.1700

Data Index: 45041 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0715. Min Act: -0.1700

Data Index: 675975 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0557. Min Act: -0.1700

Data Index: 22510 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0715. Min Act: -0.1700

Data Index: 1124657 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0715. Min Act: -0.1700

Data Index: 477526 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0715. Min Act: -0.1700

Data Index: 178057 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0400. Min Act: -0.1700

Data Index: 568945 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0715. Min Act: -0.1700

Data Index: 1007420 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0557. Min Act: -0.1700

Data Index: 322270 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0557. Min Act: -0.1700

Data Index: 785464 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0400. Min Act: -0.1700

Data Index: 305777 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0400. Min Act: -0.1700

Data Index: 539436 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 3.1661. Min Range: -3.1661

Max Act: 3.0400. Min Act: -0.1700

Data Index: 797912 (C4 (Web Text))

Max Activating Token Index: 130