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

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

Neuron 1730 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: 3.8267. Min Range: -3.8267

Max Act: 3.8267. Min Act: -0.1700

Data Index: 219243 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.7798. Min Act: -0.1700

Data Index: 510272 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.7485. Min Act: -0.1700

Data Index: 1172950 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.7641. Min Act: -0.1700

Data Index: 1045139 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6702. Min Act: -0.1700

Data Index: 467063 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6546. Min Act: -0.1700

Data Index: 1333522 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6233. Min Act: -0.1700

Data Index: 756353 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5920. Min Act: -0.1700

Data Index: 90582 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6233. Min Act: -0.1700

Data Index: 170392 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5606. Min Act: -0.1700

Data Index: 58779 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5763. Min Act: -0.1700

Data Index: 656525 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.6076. Min Act: -0.1700

Data Index: 1222577 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5450. Min Act: -0.1700

Data Index: 228872 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5450. Min Act: -0.1700

Data Index: 1654230 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5293. Min Act: -0.1700

Data Index: 135619 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5293. Min Act: -0.1700

Data Index: 1353953 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5450. Min Act: -0.1700

Data Index: 972203 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5763. Min Act: -0.1700

Data Index: 1179797 (C4 (Web Text))

Max Activating Token Index: 481

Text #18

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5293. Min Act: -0.1700

Data Index: 1485742 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 3.8267. Min Range: -3.8267

Max Act: 3.5450. Min Act: -0.1700

Data Index: 1576347 (Python Code)

Max Activating Token Index: 653