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

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

Neuron 694 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: 15.0331. Min Range: -15.0331

Max Act: 15.0331. Min Act: -0.1699

Data Index: 533017 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.7831. Min Act: -0.1699

Data Index: 582549 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.6581. Min Act: -0.1688

Data Index: 62896 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.5331. Min Act: -0.1699

Data Index: 746879 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.4706. Min Act: -0.1696

Data Index: 299358 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.5956. Min Act: -0.1698

Data Index: 935037 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.5331. Min Act: -0.1697

Data Index: 614245 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.5331. Min Act: -0.1700

Data Index: 792290 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.5331. Min Act: -0.1683

Data Index: 820120 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.5331. Min Act: -0.1688

Data Index: 1298857 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.4081. Min Act: -0.1696

Data Index: 279409 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.3456. Min Act: -0.1698

Data Index: 268835 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.4081. Min Act: -0.1700

Data Index: 743283 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.4081. Min Act: -0.1698

Data Index: 523382 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.2831. Min Act: -0.1700

Data Index: 49019 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.4081. Min Act: -0.1697

Data Index: 104337 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.3456. Min Act: -0.1700

Data Index: 962507 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.3456. Min Act: -0.1700

Data Index: 674502 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.1581. Min Act: -0.1696

Data Index: 951435 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 15.0331. Min Range: -15.0331

Max Act: 14.2831. Min Act: -0.1685

Data Index: 270336 (C4 (Web Text))

Max Activating Token Index: 190