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

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

Neuron 925 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: 5.3722. Min Range: -5.3722

Max Act: 5.3722. Min Act: -0.1700

Data Index: 273985 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.2472. Min Act: -0.1700

Data Index: 696085 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1534. Min Act: -0.1700

Data Index: 1072328 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1066. Min Act: -0.1700

Data Index: 335081 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1847. Min Act: -0.1700

Data Index: 1114886 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1534. Min Act: -0.1700

Data Index: 218202 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.1691. Min Act: -0.1700

Data Index: 357230 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.0909. Min Act: -0.1700

Data Index: 861800 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.0753. Min Act: -0.1700

Data Index: 213527 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.0284. Min Act: -0.1700

Data Index: 731779 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.0753. Min Act: -0.1700

Data Index: 458751 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 5.3722. Min Range: -5.3722

Max Act: 4.9972. Min Act: -0.1700

Data Index: 631924 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 5.3722. Min Range: -5.3722

Max Act: 4.9816. Min Act: -0.1700

Data Index: 907973 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 5.3722. Min Range: -5.3722

Max Act: 4.9972. Min Act: -0.1700

Data Index: 1190681 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.0441. Min Act: -0.1700

Data Index: 600055 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 5.3722. Min Range: -5.3722

Max Act: 4.9972. Min Act: -0.1700

Data Index: 1042518 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 5.3722. Min Range: -5.3722

Max Act: 5.0128. Min Act: -0.1700

Data Index: 147902 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 5.3722. Min Range: -5.3722

Max Act: 4.9816. Min Act: -0.1700

Data Index: 621543 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 5.3722. Min Range: -5.3722

Max Act: 4.9972. Min Act: -0.1700

Data Index: 1127449 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 5.3722. Min Range: -5.3722

Max Act: 4.9503. Min Act: -0.1700

Data Index: 78061 (C4 (Web Text))

Max Activating Token Index: 444