Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 575 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.3740. Min Act: -0.1700

Data Index: 339707 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.3583. Min Act: -0.1700

Data Index: 264324 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.3897. Min Act: -0.1700

Data Index: 1285185 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.3426. Min Act: -0.1700

Data Index: 756241 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2955. Min Act: -0.1700

Data Index: 1309956 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.3426. Min Act: -0.1700

Data Index: 108960 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.3269. Min Act: -0.1700

Data Index: 218812 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.3269. Min Act: -0.1700

Data Index: 887266 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2641. Min Act: -0.1700

Data Index: 568332 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.3112. Min Act: -0.1700

Data Index: 667239 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2484. Min Act: -0.1700

Data Index: 154513 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.3269. Min Act: -0.1700

Data Index: 295487 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2641. Min Act: -0.1700

Data Index: 651834 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2798. Min Act: -0.1700

Data Index: 1023472 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2484. Min Act: -0.1700

Data Index: 317800 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2484. Min Act: -0.1700

Data Index: 1009258 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2641. Min Act: -0.1700

Data Index: 239014 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2484. Min Act: -0.1700

Data Index: 436709 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2955. Min Act: -0.1700

Data Index: 631129 (C4 (Web Text))

Max Activating Token Index: 922

Text #19

Max Range: 3.3897. Min Range: -3.3897

Max Act: 3.2012. Min Act: -0.1700

Data Index: 952127 (C4 (Web Text))

Max Activating Token Index: 199