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

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

Neuron 2018 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1014. Min Range: -3.1014

Max Act: 3.1014. Min Act: -0.1700

Data Index: 466734 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 3.1014. Min Range: -3.1014

Max Act: 3.0067. Min Act: -0.1700

Data Index: 582373 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.9276. Min Act: -0.1700

Data Index: 482937 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.9276. Min Act: -0.1700

Data Index: 506211 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.9276. Min Act: -0.1700

Data Index: 609769 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.9117. Min Act: -0.1700

Data Index: 879183 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8959. Min Act: -0.1700

Data Index: 425437 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8800. Min Act: -0.1700

Data Index: 196967 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8800. Min Act: -0.1700

Data Index: 462834 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8800. Min Act: -0.1700

Data Index: 212536 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8323. Min Act: -0.1700

Data Index: 849110 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8323. Min Act: -0.1700

Data Index: 475548 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8164. Min Act: -0.1700

Data Index: 1248784 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8323. Min Act: -0.1700

Data Index: 518563 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8005. Min Act: -0.1700

Data Index: 65641 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8164. Min Act: -0.1700

Data Index: 1175733 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8323. Min Act: -0.1700

Data Index: 533183 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8164. Min Act: -0.1700

Data Index: 154602 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8005. Min Act: -0.1700

Data Index: 766224 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 3.1014. Min Range: -3.1014

Max Act: 2.8164. Min Act: -0.1700

Data Index: 688903 (C4 (Web Text))

Max Activating Token Index: 2