Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 383 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8777. Min Act: -0.1700

Data Index: 1077033 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.8464. Min Act: -0.1700

Data Index: 1231529 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.7526. Min Act: -0.1700

Data Index: 1121241 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.7213. Min Act: -0.1700

Data Index: 54822 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.6587. Min Act: -0.1700

Data Index: 775280 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.7213. Min Act: -0.1700

Data Index: 380407 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.6587. Min Act: -0.1700

Data Index: 858908 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.6587. Min Act: -0.1700

Data Index: 918504 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.5961. Min Act: -0.1700

Data Index: 346728 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.5647. Min Act: -0.1700

Data Index: 182917 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.6274. Min Act: -0.1700

Data Index: 871511 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.6274. Min Act: -0.1700

Data Index: 862182 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.6274. Min Act: -0.1700

Data Index: 451384 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.5647. Min Act: -0.1700

Data Index: 702874 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.6587. Min Act: -0.1700

Data Index: 1015247 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.6587. Min Act: -0.1700

Data Index: 1331102 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.5647. Min Act: -0.1700

Data Index: 1109495 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.5961. Min Act: -0.1700

Data Index: 670792 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.5334. Min Act: -0.1700

Data Index: 666866 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 3.8777. Min Range: -3.8777

Max Act: 3.5334. Min Act: -0.1700

Data Index: 380550 (C4 (Web Text))

Max Activating Token Index: 449