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

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

Neuron 1726 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.3480. Min Act: -0.1700

Data Index: 981087 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2851. Min Act: -0.1700

Data Index: 58558 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2537. Min Act: -0.1700

Data Index: 1089673 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2537. Min Act: -0.1700

Data Index: 39494 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1751. Min Act: -0.1700

Data Index: 931870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.3008. Min Act: -0.1700

Data Index: 365377 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2065. Min Act: -0.1700

Data Index: 362624 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.2223. Min Act: -0.1700

Data Index: 1231140 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1593. Min Act: -0.1700

Data Index: 978236 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1751. Min Act: -0.1700

Data Index: 843273 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1908. Min Act: -0.1700

Data Index: 87603 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1908. Min Act: -0.1700

Data Index: 851432 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1751. Min Act: -0.1700

Data Index: 786941 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1751. Min Act: -0.1700

Data Index: 730949 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1436. Min Act: -0.1700

Data Index: 815690 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1593. Min Act: -0.1700

Data Index: 672657 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1436. Min Act: -0.1700

Data Index: 1014263 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1593. Min Act: -0.1700

Data Index: 378221 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1436. Min Act: -0.1700

Data Index: 585491 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 3.3480. Min Range: -3.3480

Max Act: 3.1436. Min Act: -0.1700

Data Index: 1087145 (C4 (Web Text))

Max Activating Token Index: 589