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

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

Neuron 2032 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: 5.6259. Min Range: -5.6259

Max Act: 5.6259. Min Act: -0.1700

Data Index: 662189 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.8915. Min Act: -0.1700

Data Index: 827936 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.9072. Min Act: -0.1700

Data Index: 264495 (C4 (Web Text))

Max Activating Token Index: 341

Text #3

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.9697. Min Act: -0.1700

Data Index: 796048 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.9072. Min Act: -0.1700

Data Index: 381596 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.8759. Min Act: -0.1700

Data Index: 44818 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.8134. Min Act: -0.1700

Data Index: 1092298 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.8447. Min Act: -0.1700

Data Index: 43898 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.7821. Min Act: -0.1700

Data Index: 139694 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.7196. Min Act: -0.1700

Data Index: 677166 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.7353. Min Act: -0.1700

Data Index: 897765 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.7353. Min Act: -0.1700

Data Index: 179559 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.7196. Min Act: -0.1700

Data Index: 658843 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.6884. Min Act: -0.1700

Data Index: 838590 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.7040. Min Act: -0.1700

Data Index: 955211 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.6884. Min Act: -0.1700

Data Index: 736522 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.7040. Min Act: -0.1700

Data Index: 791453 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.6103. Min Act: -0.1700

Data Index: 343150 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.6259. Min Act: -0.1700

Data Index: 858327 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 5.6259. Min Range: -5.6259

Max Act: 4.6259. Min Act: -0.1700

Data Index: 1356820 (C4 (Web Text))

Max Activating Token Index: 637