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

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

Neuron 1612 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: 3.5779. Min Range: -3.5779

Max Act: 3.5779. Min Act: -0.1700

Data Index: 1049484 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.5153. Min Act: -0.1700

Data Index: 963135 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.5153. Min Act: -0.1700

Data Index: 1222036 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4839. Min Act: -0.1700

Data Index: 768016 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4526. Min Act: -0.1700

Data Index: 742710 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4369. Min Act: -0.1700

Data Index: 88889 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4056. Min Act: -0.1700

Data Index: 817588 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4212. Min Act: -0.1700

Data Index: 993794 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4056. Min Act: -0.1700

Data Index: 516217 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4056. Min Act: -0.1700

Data Index: 445918 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4212. Min Act: -0.1700

Data Index: 833222 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4212. Min Act: -0.1700

Data Index: 869389 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.4056. Min Act: -0.1700

Data Index: 253260 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.3899. Min Act: -0.1700

Data Index: 1203021 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.3585. Min Act: -0.1700

Data Index: 173240 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.3742. Min Act: -0.1700

Data Index: 388069 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.3742. Min Act: -0.1700

Data Index: 131056 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.3585. Min Act: -0.1700

Data Index: 1601713 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.3585. Min Act: -0.1700

Data Index: 952963 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 3.5779. Min Range: -3.5779

Max Act: 3.3428. Min Act: -0.1700

Data Index: 736711 (C4 (Web Text))

Max Activating Token Index: 70