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

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

Neuron 428 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.7035. Min Act: -0.1700

Data Index: 1174529 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.5160. Min Act: -0.1700

Data Index: 963605 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.6098. Min Act: -0.1700

Data Index: 682640 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.5785. Min Act: -0.1700

Data Index: 977782 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4848. Min Act: -0.1700

Data Index: 798733 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4848. Min Act: -0.1700

Data Index: 849795 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.5160. Min Act: -0.1700

Data Index: 760000 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4848. Min Act: -0.1700

Data Index: 274961 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.5160. Min Act: -0.1700

Data Index: 960396 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4848. Min Act: -0.1700

Data Index: 214483 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4848. Min Act: -0.1700

Data Index: 1246743 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4535. Min Act: -0.1700

Data Index: 360355 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4848. Min Act: -0.1700

Data Index: 458907 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4848. Min Act: -0.1700

Data Index: 646643 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4848. Min Act: -0.1700

Data Index: 946452 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4535. Min Act: -0.1700

Data Index: 669374 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4223. Min Act: -0.1700

Data Index: 1161605 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4848. Min Act: -0.1700

Data Index: 271014 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.3910. Min Act: -0.1700

Data Index: 32979 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 5.7035. Min Range: -5.7035

Max Act: 5.4535. Min Act: -0.1700

Data Index: 120251 (C4 (Web Text))

Max Activating Token Index: 274