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

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

Neuron 1890 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0984. Min Range: -5.0984

Max Act: 5.0984. Min Act: -0.1700

Data Index: 238889 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8797. Min Act: -0.1700

Data Index: 478550 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8172. Min Act: -0.1700

Data Index: 435359 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8172. Min Act: -0.1700

Data Index: 1151541 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.7859. Min Act: -0.1700

Data Index: 671822 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.7859. Min Act: -0.1700

Data Index: 516069 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.8484. Min Act: -0.1700

Data Index: 1251769 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.7547. Min Act: -0.1700

Data Index: 653070 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.6609. Min Act: -0.1700

Data Index: 1282263 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.6609. Min Act: -0.1700

Data Index: 615178 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.6609. Min Act: -0.1700

Data Index: 198464 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.5984. Min Act: -0.1700

Data Index: 1010959 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.6922. Min Act: -0.1700

Data Index: 501173 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.6297. Min Act: -0.1700

Data Index: 753454 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.6609. Min Act: -0.1700

Data Index: 305036 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.5984. Min Act: -0.1700

Data Index: 1043431 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.5984. Min Act: -0.1700

Data Index: 329189 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.6297. Min Act: -0.1700

Data Index: 597187 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.5672. Min Act: -0.1700

Data Index: 70341 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 5.0984. Min Range: -5.0984

Max Act: 4.5672. Min Act: -0.1700

Data Index: 1091947 (C4 (Web Text))

Max Activating Token Index: 857