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

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

Neuron 1936 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: 5.9738. Min Range: -5.9738

Max Act: 5.8488. Min Act: -0.1700

Data Index: 853121 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.9425. Min Act: -0.1700

Data Index: 584405 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.9738. Min Act: -0.1700

Data Index: 820008 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.8175. Min Act: -0.1700

Data Index: 1154496 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.8488. Min Act: -0.1700

Data Index: 1178602 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.8175. Min Act: -0.1700

Data Index: 704685 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.8488. Min Act: -0.1700

Data Index: 845344 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.8488. Min Act: -0.1700

Data Index: 225260 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.7550. Min Act: -0.1700

Data Index: 100386 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.8488. Min Act: -0.1700

Data Index: 977958 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.7550. Min Act: -0.1700

Data Index: 1085135 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.7550. Min Act: -0.1700

Data Index: 135677 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.7863. Min Act: -0.1700

Data Index: 849184 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.8488. Min Act: -0.1700

Data Index: 634213 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.7863. Min Act: -0.1700

Data Index: 515770 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.7863. Min Act: -0.1700

Data Index: 676028 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.7550. Min Act: -0.1700

Data Index: 1081136 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.6925. Min Act: -0.1700

Data Index: 136602 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.7238. Min Act: -0.1700

Data Index: 1046152 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 5.9738. Min Range: -5.9738

Max Act: 5.7550. Min Act: -0.1700

Data Index: 534526 (C4 (Web Text))

Max Activating Token Index: 319