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

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

Neuron 1673 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: 5.1414. Min Range: -5.1414

Max Act: 5.1414. Min Act: -0.1700

Data Index: 803425 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 5.1414. Min Range: -5.1414

Max Act: 5.1414. Min Act: -0.1700

Data Index: 149966 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 5.1414. Min Range: -5.1414

Max Act: 5.0164. Min Act: -0.1700

Data Index: 1085885 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 5.1414. Min Range: -5.1414

Max Act: 5.0164. Min Act: -0.1700

Data Index: 1029376 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 5.1414. Min Range: -5.1414

Max Act: 5.0476. Min Act: -0.1700

Data Index: 13509 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.9851. Min Act: -0.1700

Data Index: 271646 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.9851. Min Act: -0.1700

Data Index: 820236 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.9851. Min Act: -0.1700

Data Index: 418893 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.9539. Min Act: -0.1700

Data Index: 344918 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.9226. Min Act: -0.1700

Data Index: 1079974 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.9539. Min Act: -0.1700

Data Index: 268868 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.9539. Min Act: -0.1700

Data Index: 549660 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.8601. Min Act: -0.1700

Data Index: 1003749 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.8914. Min Act: -0.1700

Data Index: 268068 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.8914. Min Act: -0.1700

Data Index: 721993 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.8601. Min Act: -0.1700

Data Index: 1256194 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.8601. Min Act: -0.1700

Data Index: 336464 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.8601. Min Act: -0.1700

Data Index: 1130972 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.7664. Min Act: -0.1700

Data Index: 1217968 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 5.1414. Min Range: -5.1414

Max Act: 4.8289. Min Act: -0.1700

Data Index: 936930 (C4 (Web Text))

Max Activating Token Index: 325