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

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

Neuron 624 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: 3.0433. Min Range: -3.0433

Max Act: 3.0433. Min Act: -0.1700

Data Index: 717672 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 3.0433. Min Range: -3.0433

Max Act: 3.0117. Min Act: -0.1700

Data Index: 1158146 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9959. Min Act: -0.1700

Data Index: 265207 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9484. Min Act: -0.1700

Data Index: 148872 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9326. Min Act: -0.1700

Data Index: 251498 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9168. Min Act: -0.1700

Data Index: 250140 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9168. Min Act: -0.1700

Data Index: 580058 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9009. Min Act: -0.1700

Data Index: 1375 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9168. Min Act: -0.1700

Data Index: 1013141 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9009. Min Act: -0.1700

Data Index: 1003785 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9326. Min Act: -0.1700

Data Index: 959750 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9168. Min Act: -0.1700

Data Index: 1343903 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.8850. Min Act: -0.1700

Data Index: 78670 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.9168. Min Act: -0.1700

Data Index: 1044641 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.8850. Min Act: -0.1700

Data Index: 235140 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.8850. Min Act: -0.1700

Data Index: 709765 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.8533. Min Act: -0.1700

Data Index: 714562 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.8850. Min Act: -0.1700

Data Index: 229597 (C4 (Web Text))

Max Activating Token Index: 543

Text #18

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.8692. Min Act: -0.1700

Data Index: 251860 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 3.0433. Min Range: -3.0433

Max Act: 2.8374. Min Act: -0.1700

Data Index: 2912 (C4 (Web Text))

Max Activating Token Index: 522