Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 152 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.5087. Min Act: -0.1700

Data Index: 980452 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.4462. Min Act: -0.1700

Data Index: 1250125 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.4150. Min Act: -0.1700

Data Index: 930413 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.4150. Min Act: -0.1700

Data Index: 792801 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.4150. Min Act: -0.1700

Data Index: 1137360 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.4150. Min Act: -0.1700

Data Index: 1216216 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.3525. Min Act: -0.1700

Data Index: 125679 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.3837. Min Act: -0.1700

Data Index: 112177 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.4775. Min Act: -0.1700

Data Index: 885589 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.3212. Min Act: -0.1700

Data Index: 808361 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.2275. Min Act: -0.1700

Data Index: 1191076 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.2900. Min Act: -0.1700

Data Index: 559586 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.3212. Min Act: -0.1700

Data Index: 683319 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.2900. Min Act: -0.1700

Data Index: 1188512 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.1962. Min Act: -0.1700

Data Index: 25199 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.2900. Min Act: -0.1700

Data Index: 431813 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.2275. Min Act: -0.1700

Data Index: 445891 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.1962. Min Act: -0.1700

Data Index: 355288 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.2275. Min Act: -0.1700

Data Index: 160702 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 5.5087. Min Range: -5.5087

Max Act: 5.1962. Min Act: -0.1700

Data Index: 1154078 (C4 (Web Text))

Max Activating Token Index: 720