Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1948 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.9083. Min Act: -0.1700

Data Index: 573368 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.7521. Min Act: -0.1700

Data Index: 1097370 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.4396. Min Act: -0.1700

Data Index: 1179468 (C4 (Web Text))

Max Activating Token Index: 534

Text #3

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.4708. Min Act: -0.1699

Data Index: 76514 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.3771. Min Act: -0.1699

Data Index: 1081892 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.1896. Min Act: -0.1700

Data Index: 157791 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.2833. Min Act: -0.1699

Data Index: 1207836 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.2833. Min Act: -0.1699

Data Index: 214680 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.1896. Min Act: -0.1700

Data Index: 808797 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.2521. Min Act: -0.1699

Data Index: 181713 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.2208. Min Act: -0.1700

Data Index: 893731 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.1271. Min Act: -0.1700

Data Index: 48301 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.1896. Min Act: -0.1700

Data Index: 1334894 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.0958. Min Act: -0.1700

Data Index: 254453 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.3771. Min Act: -0.1700

Data Index: 1293177 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.0646. Min Act: -0.1700

Data Index: 300165 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.1896. Min Act: -0.1699

Data Index: 437013 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.3458. Min Act: -0.1700

Data Index: 1303306 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.0958. Min Act: -0.1700

Data Index: 929363 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 7.9083. Min Range: -7.9083

Max Act: 7.2208. Min Act: -0.1699

Data Index: 1072033 (C4 (Web Text))

Max Activating Token Index: 474