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

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

Neuron 685 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.4434. Min Act: -0.1700

Data Index: 32113 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.4122. Min Act: -0.1700

Data Index: 110833 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.1934. Min Act: -0.1700

Data Index: 947867 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.0997. Min Act: -0.1700

Data Index: 753388 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.1309. Min Act: -0.1700

Data Index: 1469951 (Python Code)

Max Activating Token Index: 891

Text #5

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.0684. Min Act: -0.1700

Data Index: 443060 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.0684. Min Act: -0.1700

Data Index: 452921 (C4 (Web Text))

Max Activating Token Index: 478

Text #7

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.0684. Min Act: -0.1700

Data Index: 649652 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.0372. Min Act: -0.1700

Data Index: 1257650 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.0372. Min Act: -0.1700

Data Index: 1696 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 5.4434. Min Range: -5.4434

Max Act: 4.9747. Min Act: -0.1700

Data Index: 179053 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 5.4434. Min Range: -5.4434

Max Act: 4.9747. Min Act: -0.1700

Data Index: 735248 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.0059. Min Act: -0.1700

Data Index: 266945 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 5.4434. Min Range: -5.4434

Max Act: 4.9747. Min Act: -0.1700

Data Index: 475902 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 5.4434. Min Range: -5.4434

Max Act: 5.0059. Min Act: -0.1700

Data Index: 1328513 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 5.4434. Min Range: -5.4434

Max Act: 4.9434. Min Act: -0.1700

Data Index: 1301299 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 5.4434. Min Range: -5.4434

Max Act: 4.9122. Min Act: -0.1700

Data Index: 1135448 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 5.4434. Min Range: -5.4434

Max Act: 4.9434. Min Act: -0.1700

Data Index: 1216529 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 5.4434. Min Range: -5.4434

Max Act: 4.9122. Min Act: -0.1700

Data Index: 80882 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 5.4434. Min Range: -5.4434

Max Act: 4.9434. Min Act: -0.1700

Data Index: 357398 (C4 (Web Text))

Max Activating Token Index: 511