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

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

Neuron 742 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: 5.6659. Min Range: -5.6659

Max Act: 5.6659. Min Act: -0.1700

Data Index: 11541 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.3222. Min Act: -0.1700

Data Index: 1020785 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.2597. Min Act: -0.1700

Data Index: 67794 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.2597. Min Act: -0.1700

Data Index: 196761 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.2284. Min Act: -0.1700

Data Index: 727929 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.2597. Min Act: -0.1700

Data Index: 339131 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.2284. Min Act: -0.1700

Data Index: 476961 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.1347. Min Act: -0.1699

Data Index: 956166 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.1347. Min Act: -0.1700

Data Index: 1301904 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.1347. Min Act: -0.1700

Data Index: 1028353 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.1034. Min Act: -0.1700

Data Index: 911580 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.1347. Min Act: -0.1700

Data Index: 3352 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.0722. Min Act: -0.1700

Data Index: 937922 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.0722. Min Act: -0.1700

Data Index: 904363 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.0722. Min Act: -0.1700

Data Index: 554139 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.0409. Min Act: -0.1700

Data Index: 866586 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.0097. Min Act: -0.1700

Data Index: 307966 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 5.6659. Min Range: -5.6659

Max Act: 4.9784. Min Act: -0.1700

Data Index: 909098 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 5.6659. Min Range: -5.6659

Max Act: 5.0097. Min Act: -0.1700

Data Index: 931885 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 5.6659. Min Range: -5.6659

Max Act: 4.9784. Min Act: -0.1700

Data Index: 633296 (C4 (Web Text))

Max Activating Token Index: 915