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

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

Neuron 1414 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: 5.4114. Min Range: -5.4114

Max Act: 5.4114. Min Act: -0.1700

Data Index: 608122 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.3801. Min Act: -0.1700

Data Index: 28950 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.3489. Min Act: -0.1700

Data Index: 1249438 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.3176. Min Act: -0.1700

Data Index: 1074162 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.2239. Min Act: -0.1700

Data Index: 448318 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.2551. Min Act: -0.1700

Data Index: 774262 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.2239. Min Act: -0.1700

Data Index: 1036514 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.2239. Min Act: -0.1700

Data Index: 183154 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.2551. Min Act: -0.1700

Data Index: 915826 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.2239. Min Act: -0.1700

Data Index: 139043 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1614. Min Act: -0.1700

Data Index: 477234 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1926. Min Act: -0.1700

Data Index: 1012265 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1926. Min Act: -0.1700

Data Index: 289840 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1926. Min Act: -0.1700

Data Index: 483074 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1926. Min Act: -0.1700

Data Index: 218027 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1614. Min Act: -0.1700

Data Index: 1174917 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1614. Min Act: -0.1700

Data Index: 1359345 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1926. Min Act: -0.1700

Data Index: 1108109 (C4 (Web Text))

Max Activating Token Index: 477

Text #18

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1614. Min Act: -0.1700

Data Index: 631667 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 5.4114. Min Range: -5.4114

Max Act: 5.1301. Min Act: -0.1700

Data Index: 1107860 (C4 (Web Text))

Max Activating Token Index: 305