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

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

Neuron 407 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: 5.1332. Min Range: -5.1332

Max Act: 5.1332. Min Act: -0.1700

Data Index: 1252656 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 5.1332. Min Range: -5.1332

Max Act: 5.1019. Min Act: -0.1700

Data Index: 259711 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 5.1332. Min Range: -5.1332

Max Act: 5.0707. Min Act: -0.1700

Data Index: 1182743 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 5.1332. Min Range: -5.1332

Max Act: 5.0394. Min Act: -0.1700

Data Index: 78038 (C4 (Web Text))

Max Activating Token Index: 141

Text #4

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.9144. Min Act: -0.1700

Data Index: 1123363 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.9457. Min Act: -0.1700

Data Index: 205760 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.8832. Min Act: -0.1700

Data Index: 1318459 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.7894. Min Act: -0.1700

Data Index: 170541 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.7269. Min Act: -0.1700

Data Index: 699629 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.7269. Min Act: -0.1700

Data Index: 898919 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.7582. Min Act: -0.1700

Data Index: 355323 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.6957. Min Act: -0.1700

Data Index: 1104613 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.7269. Min Act: -0.1700

Data Index: 192991 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.6957. Min Act: -0.1700

Data Index: 570971 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.6644. Min Act: -0.1700

Data Index: 935111 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.6957. Min Act: -0.1700

Data Index: 254786 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.6957. Min Act: -0.1700

Data Index: 844445 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.6957. Min Act: -0.1700

Data Index: 820608 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.6332. Min Act: -0.1700

Data Index: 616982 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 5.1332. Min Range: -5.1332

Max Act: 4.6332. Min Act: -0.1700

Data Index: 536994 (C4 (Web Text))

Max Activating Token Index: 321