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

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

Neuron 1834 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: 5.8441. Min Range: -5.8441

Max Act: 5.8441. Min Act: -0.1700

Data Index: 20453 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5941. Min Act: -0.1700

Data Index: 1157018 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5941. Min Act: -0.1700

Data Index: 181547 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5941. Min Act: -0.1700

Data Index: 508822 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5316. Min Act: -0.1700

Data Index: 173503 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5316. Min Act: -0.1700

Data Index: 387903 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5629. Min Act: -0.1700

Data Index: 125077 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5629. Min Act: -0.1700

Data Index: 246986 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5629. Min Act: -0.1700

Data Index: 1267301 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5004. Min Act: -0.1700

Data Index: 1078409 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.4379. Min Act: -0.1700

Data Index: 1188826 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.4691. Min Act: -0.1700

Data Index: 19376 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.3441. Min Act: -0.1700

Data Index: 412319 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5004. Min Act: -0.1700

Data Index: 463494 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.4691. Min Act: -0.1700

Data Index: 1023470 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.5004. Min Act: -0.1700

Data Index: 999901 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.4691. Min Act: -0.1700

Data Index: 361406 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.4379. Min Act: -0.1700

Data Index: 140051 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.4379. Min Act: -0.1700

Data Index: 2828 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 5.8441. Min Range: -5.8441

Max Act: 5.4379. Min Act: -0.1700

Data Index: 466994 (C4 (Web Text))

Max Activating Token Index: 50