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

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

Neuron 1557 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: 7.8982. Min Range: -7.8982

Max Act: 7.8982. Min Act: -0.1700

Data Index: 448547 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.7107. Min Act: -0.1700

Data Index: 112344 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.3670. Min Act: -0.1700

Data Index: 481364 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.4295. Min Act: -0.1700

Data Index: 114769 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.3670. Min Act: -0.1700

Data Index: 976459 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.3045. Min Act: -0.1700

Data Index: 296313 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.3045. Min Act: -0.1700

Data Index: 449521 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.2732. Min Act: -0.1700

Data Index: 1120670 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.1482. Min Act: -0.1700

Data Index: 377333 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.2732. Min Act: -0.1700

Data Index: 744891 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.1170. Min Act: -0.1700

Data Index: 265705 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.2107. Min Act: -0.1700

Data Index: 942219 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.2420. Min Act: -0.1700

Data Index: 822136 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.1482. Min Act: -0.1700

Data Index: 374938 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.1795. Min Act: -0.1700

Data Index: 670468 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.2107. Min Act: -0.1700

Data Index: 1218137 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.2732. Min Act: -0.1700

Data Index: 1203495 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.1170. Min Act: -0.1700

Data Index: 386817 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.2107. Min Act: -0.1700

Data Index: 1627799 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 7.8982. Min Range: -7.8982

Max Act: 7.1482. Min Act: -0.1700

Data Index: 519296 (C4 (Web Text))

Max Activating Token Index: 760