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

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

Neuron 354 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: 3.3389. Min Range: -3.3389

Max Act: 3.3389. Min Act: -0.1700

Data Index: 191673 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.2604. Min Act: -0.1700

Data Index: 953004 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.2289. Min Act: -0.1700

Data Index: 1268897 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.2447. Min Act: -0.1700

Data Index: 538224 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.2447. Min Act: -0.1700

Data Index: 531846 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.2289. Min Act: -0.1700

Data Index: 46143 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.2132. Min Act: -0.1700

Data Index: 638927 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.2132. Min Act: -0.1700

Data Index: 920841 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1975. Min Act: -0.1700

Data Index: 1223777 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.2132. Min Act: -0.1700

Data Index: 1319125 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1817. Min Act: -0.1700

Data Index: 1319006 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1817. Min Act: -0.1700

Data Index: 31440 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1660. Min Act: -0.1700

Data Index: 301279 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1660. Min Act: -0.1700

Data Index: 1349212 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1660. Min Act: -0.1700

Data Index: 316033 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1660. Min Act: -0.1700

Data Index: 458390 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1503. Min Act: -0.1700

Data Index: 1174537 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1660. Min Act: -0.1700

Data Index: 687517 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1660. Min Act: -0.1700

Data Index: 702426 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 3.3389. Min Range: -3.3389

Max Act: 3.1503. Min Act: -0.1700

Data Index: 84048 (C4 (Web Text))

Max Activating Token Index: 768