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

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

Neuron 1129 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.4159. Min Act: -0.1700

Data Index: 169164 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.4002. Min Act: -0.1700

Data Index: 1260768 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.3845. Min Act: -0.1700

Data Index: 940583 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.4002. Min Act: -0.1700

Data Index: 629929 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.4002. Min Act: -0.1700

Data Index: 1292756 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.4316. Min Act: -0.1700

Data Index: 296632 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.3374. Min Act: -0.1700

Data Index: 1341049 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2746. Min Act: -0.1700

Data Index: 1130676 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.3217. Min Act: -0.1700

Data Index: 833166 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2432. Min Act: -0.1700

Data Index: 110592 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2746. Min Act: -0.1700

Data Index: 36755 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2746. Min Act: -0.1700

Data Index: 1170218 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2589. Min Act: -0.1700

Data Index: 523705 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2589. Min Act: -0.1700

Data Index: 730079 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2589. Min Act: -0.1700

Data Index: 1192783 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2275. Min Act: -0.1700

Data Index: 751275 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2432. Min Act: -0.1700

Data Index: 1050395 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.1960. Min Act: -0.1700

Data Index: 1325217 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2117. Min Act: -0.1700

Data Index: 693174 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.4316. Min Range: -3.4316

Max Act: 3.2117. Min Act: -0.1700

Data Index: 1092878 (C4 (Web Text))

Max Activating Token Index: 795