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

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

Neuron 1122 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: 3.6007. Min Range: -3.6007

Max Act: 3.6007. Min Act: -0.1700

Data Index: 370594 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5224. Min Act: -0.1700

Data Index: 991855 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5224. Min Act: -0.1700

Data Index: 487361 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5224. Min Act: -0.1700

Data Index: 956469 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5224. Min Act: -0.1700

Data Index: 398508 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5068. Min Act: -0.1700

Data Index: 214522 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5068. Min Act: -0.1700

Data Index: 131723 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5068. Min Act: -0.1700

Data Index: 197009 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.5068. Min Act: -0.1700

Data Index: 738016 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4911. Min Act: -0.1699

Data Index: 546802 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4754. Min Act: -0.1700

Data Index: 275017 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4754. Min Act: -0.1700

Data Index: 211130 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4598. Min Act: -0.1700

Data Index: 563049 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4598. Min Act: -0.1700

Data Index: 260118 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4441. Min Act: -0.1700

Data Index: 15276 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4441. Min Act: -0.1700

Data Index: 325401 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4441. Min Act: -0.1700

Data Index: 713675 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4441. Min Act: -0.1700

Data Index: 258470 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4441. Min Act: -0.1700

Data Index: 551129 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 3.6007. Min Range: -3.6007

Max Act: 3.4441. Min Act: -0.1700

Data Index: 857296 (C4 (Web Text))

Max Activating Token Index: 917