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

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

Neuron 109 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: 5.1013. Min Range: -5.1013

Max Act: 5.1013. Min Act: -0.1700

Data Index: 307080 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 5.1013. Min Range: -5.1013

Max Act: 5.0701. Min Act: -0.1700

Data Index: 482968 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 5.1013. Min Range: -5.1013

Max Act: 5.0388. Min Act: -0.1700

Data Index: 254076 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 5.1013. Min Range: -5.1013

Max Act: 5.0388. Min Act: -0.1700

Data Index: 945288 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 5.1013. Min Range: -5.1013

Max Act: 5.0701. Min Act: -0.1700

Data Index: 1021222 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.9919. Min Act: -0.1700

Data Index: 76867 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.9294. Min Act: -0.1700

Data Index: 579828 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8826. Min Act: -0.1700

Data Index: 782746 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.9294. Min Act: -0.1700

Data Index: 1352987 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.9294. Min Act: -0.1700

Data Index: 411045 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8982. Min Act: -0.1700

Data Index: 97223 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8826. Min Act: -0.1700

Data Index: 21529 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8513. Min Act: -0.1700

Data Index: 977099 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8669. Min Act: -0.1700

Data Index: 519820 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8513. Min Act: -0.1700

Data Index: 883910 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8357. Min Act: -0.1700

Data Index: 190606 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8513. Min Act: -0.1700

Data Index: 395719 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8513. Min Act: -0.1700

Data Index: 816511 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8201. Min Act: -0.1700

Data Index: 205595 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 5.1013. Min Range: -5.1013

Max Act: 4.8357. Min Act: -0.1700

Data Index: 846079 (C4 (Web Text))

Max Activating Token Index: 509