Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 753 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.3183. Min Act: -0.1700

Data Index: 1221891 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.3183. Min Act: -0.1700

Data Index: 81431 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.3183. Min Act: -0.1700

Data Index: 866739 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.3183. Min Act: -0.1700

Data Index: 361797 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.3808. Min Act: -0.1700

Data Index: 139702 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.2558. Min Act: -0.1700

Data Index: 229678 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1621. Min Act: -0.1700

Data Index: 836118 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1308. Min Act: -0.1700

Data Index: 758166 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1308. Min Act: -0.1700

Data Index: 695704 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1933. Min Act: -0.1700

Data Index: 902276 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1621. Min Act: -0.1700

Data Index: 216358 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1621. Min Act: -0.1700

Data Index: 320585 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1308. Min Act: -0.1699

Data Index: 579509 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.2558. Min Act: -0.1700

Data Index: 190304 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1308. Min Act: -0.1700

Data Index: 117355 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1933. Min Act: -0.1700

Data Index: 1289437 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1621. Min Act: -0.1700

Data Index: 1223216 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.0996. Min Act: -0.1700

Data Index: 87526 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1308. Min Act: -0.1700

Data Index: 480331 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 8.3808. Min Range: -8.3808

Max Act: 8.1308. Min Act: -0.1700

Data Index: 308532 (C4 (Web Text))

Max Activating Token Index: 155