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

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

Neuron 1927 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1890. Min Range: -3.1890

Max Act: 3.1890. Min Act: -0.1700

Data Index: 551360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.8412. Min Act: -0.1700

Data Index: 234005 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.7935. Min Act: -0.1700

Data Index: 87620 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.7776. Min Act: -0.1700

Data Index: 231396 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.7616. Min Act: -0.1700

Data Index: 139325 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.7297. Min Act: -0.1700

Data Index: 498789 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6977. Min Act: -0.1700

Data Index: 678603 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6657. Min Act: -0.1700

Data Index: 1357989 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6336. Min Act: -0.1700

Data Index: 348390 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6496. Min Act: -0.1700

Data Index: 427296 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6336. Min Act: -0.1700

Data Index: 974265 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6175. Min Act: -0.1700

Data Index: 1229357 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6014. Min Act: -0.1700

Data Index: 1016346 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6014. Min Act: -0.1700

Data Index: 1541457 (Python Code)

Max Activating Token Index: 319

Text #14

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6014. Min Act: -0.1700

Data Index: 68066 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.5853. Min Act: -0.1700

Data Index: 1133747 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.5853. Min Act: -0.1700

Data Index: 1265342 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.6014. Min Act: -0.1700

Data Index: 1215067 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.5853. Min Act: -0.1700

Data Index: 831168 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 3.1890. Min Range: -3.1890

Max Act: 2.5692. Min Act: -0.1700

Data Index: 1325086 (C4 (Web Text))

Max Activating Token Index: 622