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

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

Neuron 1246 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: 7.2267. Min Range: -7.2267

Max Act: 7.2267. Min Act: -0.1700

Data Index: 907325 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 7.2267. Min Range: -7.2267

Max Act: 7.0079. Min Act: -0.1700

Data Index: 1202919 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.9767. Min Act: -0.1700

Data Index: 1159129 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.9142. Min Act: -0.1700

Data Index: 184605 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.8517. Min Act: -0.1698

Data Index: 565188 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.7267. Min Act: -0.1700

Data Index: 1251603 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.8517. Min Act: -0.1700

Data Index: 1244804 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.7579. Min Act: -0.1700

Data Index: 1133152 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.7267. Min Act: -0.1700

Data Index: 792977 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.8204. Min Act: -0.1700

Data Index: 1264668 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.7267. Min Act: -0.1700

Data Index: 1322430 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.6642. Min Act: -0.1700

Data Index: 888252 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.7579. Min Act: -0.1700

Data Index: 261222 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.7267. Min Act: -0.1700

Data Index: 1068503 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.6954. Min Act: -0.1700

Data Index: 923050 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.6329. Min Act: -0.1700

Data Index: 407786 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.6017. Min Act: -0.1700

Data Index: 702596 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.6329. Min Act: -0.1700

Data Index: 370229 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.5704. Min Act: -0.1700

Data Index: 1209731 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 7.2267. Min Range: -7.2267

Max Act: 6.5392. Min Act: -0.1700

Data Index: 580607 (C4 (Web Text))

Max Activating Token Index: 705