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

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

Neuron 679 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: 5.5825. Min Range: -5.5825

Max Act: 5.5825. Min Act: -0.1700

Data Index: 933127 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.3950. Min Act: -0.1700

Data Index: 570382 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.3012. Min Act: -0.1700

Data Index: 874877 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.3637. Min Act: -0.1700

Data Index: 135283 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.3012. Min Act: -0.1700

Data Index: 604749 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.3012. Min Act: -0.1700

Data Index: 1191032 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2700. Min Act: -0.1700

Data Index: 711307 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.3012. Min Act: -0.1700

Data Index: 1333875 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.3012. Min Act: -0.1700

Data Index: 521370 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2075. Min Act: -0.1700

Data Index: 909693 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2387. Min Act: -0.1700

Data Index: 62723 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2387. Min Act: -0.1700

Data Index: 5924 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2387. Min Act: -0.1700

Data Index: 635677 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2387. Min Act: -0.1700

Data Index: 234411 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2075. Min Act: -0.1700

Data Index: 441086 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2387. Min Act: -0.1700

Data Index: 699085 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2075. Min Act: -0.1700

Data Index: 1009908 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2075. Min Act: -0.1700

Data Index: 1156289 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2075. Min Act: -0.1700

Data Index: 904866 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 5.5825. Min Range: -5.5825

Max Act: 5.2075. Min Act: -0.1700

Data Index: 1102407 (C4 (Web Text))

Max Activating Token Index: 1000