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

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

Neuron 447 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: 7.8219. Min Range: -7.8219

Max Act: 7.8219. Min Act: -0.1700

Data Index: 525849 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.6344. Min Act: -0.1700

Data Index: 1177406 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.5719. Min Act: -0.1700

Data Index: 56835 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.5719. Min Act: -0.1700

Data Index: 310856 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.5094. Min Act: -0.1700

Data Index: 537693 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.4469. Min Act: -0.1700

Data Index: 1280486 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.4469. Min Act: -0.1700

Data Index: 6342 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.4469. Min Act: -0.1700

Data Index: 867966 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.3219. Min Act: -0.1700

Data Index: 717311 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.2594. Min Act: -0.1698

Data Index: 513977 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.2594. Min Act: -0.1700

Data Index: 1309280 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.2594. Min Act: -0.1696

Data Index: 1307802 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.3219. Min Act: -0.1699

Data Index: 199258 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.3844. Min Act: -0.1699

Data Index: 750569 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.3844. Min Act: -0.1700

Data Index: 587994 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.2594. Min Act: -0.1699

Data Index: 1139415 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.2594. Min Act: -0.1695

Data Index: 946256 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.2594. Min Act: -0.1699

Data Index: 539026 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.2594. Min Act: -0.1700

Data Index: 1295768 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 7.8219. Min Range: -7.8219

Max Act: 7.2594. Min Act: -0.1700

Data Index: 376503 (C4 (Web Text))

Max Activating Token Index: 364