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

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

Neuron 189 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: 5.4269. Min Range: -5.4269

Max Act: 5.4269. Min Act: -0.1700

Data Index: 403359 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.2394. Min Act: -0.1700

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.2394. Min Act: -0.1700

Data Index: 757595 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.2082. Min Act: -0.1700

Data Index: 1205277 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.1769. Min Act: -0.1700

Data Index: 806621 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.1769. Min Act: -0.1700

Data Index: 1219392 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.1457. Min Act: -0.1700

Data Index: 132545 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.0832. Min Act: -0.1700

Data Index: 746187 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.1769. Min Act: -0.1700

Data Index: 309907 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.1457. Min Act: -0.1700

Data Index: 727506 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.1457. Min Act: -0.1700

Data Index: 443786 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.1457. Min Act: -0.1700

Data Index: 1217434 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.1144. Min Act: -0.1700

Data Index: 650841 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.0207. Min Act: -0.1700

Data Index: 755616 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.0832. Min Act: -0.1700

Data Index: 423539 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.1144. Min Act: -0.1700

Data Index: 165748 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.0519. Min Act: -0.1700

Data Index: 1204959 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.0832. Min Act: -0.1700

Data Index: 742588 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.0832. Min Act: -0.1700

Data Index: 366876 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 5.4269. Min Range: -5.4269

Max Act: 5.0519. Min Act: -0.1700

Data Index: 902676 (C4 (Web Text))

Max Activating Token Index: 734