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

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

Neuron 1354 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: 5.2813. Min Range: -5.2813

Max Act: 5.2501. Min Act: -0.1700

Data Index: 762052 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 5.2813. Min Range: -5.2813

Max Act: 5.2813. Min Act: -0.1699

Data Index: 719688 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 5.2813. Min Range: -5.2813

Max Act: 5.0938. Min Act: -0.1700

Data Index: 350974 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 5.2813. Min Range: -5.2813

Max Act: 5.1563. Min Act: -0.1699

Data Index: 46765 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 5.2813. Min Range: -5.2813

Max Act: 5.0313. Min Act: -0.1700

Data Index: 884769 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 5.2813. Min Range: -5.2813

Max Act: 5.0313. Min Act: -0.1700

Data Index: 1306137 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 5.2813. Min Range: -5.2813

Max Act: 5.0313. Min Act: -0.1700

Data Index: 284246 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 5.2813. Min Range: -5.2813

Max Act: 5.0001. Min Act: -0.1700

Data Index: 1244014 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 5.2813. Min Range: -5.2813

Max Act: 5.0001. Min Act: -0.1700

Data Index: 272365 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.9688. Min Act: -0.1700

Data Index: 274611 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.8751. Min Act: -0.1700

Data Index: 624235 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.9063. Min Act: -0.1700

Data Index: 1219727 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.9063. Min Act: -0.1700

Data Index: 1261848 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.9376. Min Act: -0.1700

Data Index: 839508 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.8438. Min Act: -0.1699

Data Index: 1779 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.8751. Min Act: -0.1700

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.8751. Min Act: -0.1700

Data Index: 388103 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.8751. Min Act: -0.1700

Data Index: 158445 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.8751. Min Act: -0.1700

Data Index: 700663 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 5.2813. Min Range: -5.2813

Max Act: 4.8438. Min Act: -0.1700

Data Index: 678959 (C4 (Web Text))

Max Activating Token Index: 149