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

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

Neuron 518 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.7830. Min Act: -0.1700

Data Index: 771162 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.6580. Min Act: -0.1700

Data Index: 259527 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.5017. Min Act: -0.1700

Data Index: 871882 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.5330. Min Act: -0.1700

Data Index: 1087272 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.4705. Min Act: -0.1700

Data Index: 476482 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.4392. Min Act: -0.1700

Data Index: 816722 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.4392. Min Act: -0.1700

Data Index: 110103 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.4080. Min Act: -0.1700

Data Index: 1070316 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.4080. Min Act: -0.1700

Data Index: 751391 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.4705. Min Act: -0.1700

Data Index: 249780 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.4392. Min Act: -0.1700

Data Index: 1050961 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.4080. Min Act: -0.1700

Data Index: 444884 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.4080. Min Act: -0.1700

Data Index: 1015012 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.3767. Min Act: -0.1700

Data Index: 729666 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.3455. Min Act: -0.1700

Data Index: 645884 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.3142. Min Act: -0.1700

Data Index: 1047852 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.3767. Min Act: -0.1700

Data Index: 48958 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.3142. Min Act: -0.1700

Data Index: 78466 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.3142. Min Act: -0.1700

Data Index: 913247 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 5.7830. Min Range: -5.7830

Max Act: 5.3142. Min Act: -0.1700

Data Index: 238819 (C4 (Web Text))

Max Activating Token Index: 211