Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 414 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.7589. Min Act: -0.1700

Data Index: 1150614 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.6339. Min Act: -0.1700

Data Index: 116470 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.6339. Min Act: -0.1700

Data Index: 315384 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.4151. Min Act: -0.1699

Data Index: 268203 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.4151. Min Act: -0.1700

Data Index: 265438 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.3214. Min Act: -0.1700

Data Index: 1121419 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2589. Min Act: -0.1700

Data Index: 1206591 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2276. Min Act: -0.1700

Data Index: 1088927 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2276. Min Act: -0.1700

Data Index: 1223985 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2589. Min Act: -0.1700

Data Index: 93017 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2589. Min Act: -0.1700

Data Index: 452410 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2276. Min Act: -0.1700

Data Index: 1098379 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2276. Min Act: -0.1700

Data Index: 304997 (C4 (Web Text))

Max Activating Token Index: 82

Text #13

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.1339. Min Act: -0.1700

Data Index: 1074106 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2589. Min Act: -0.1700

Data Index: 240561 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2276. Min Act: -0.1700

Data Index: 695098 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.1964. Min Act: -0.1700

Data Index: 149248 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.2589. Min Act: -0.1700

Data Index: 795992 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.1964. Min Act: -0.1700

Data Index: 569444 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 5.7589. Min Range: -5.7589

Max Act: 5.1651. Min Act: -0.1700

Data Index: 131812 (C4 (Web Text))

Max Activating Token Index: 823