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

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

Neuron 1026 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.7701. Min Act: -0.1700

Data Index: 1539551 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.4576. Min Act: -0.1700

Data Index: 1574408 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.4264. Min Act: -0.1700

Data Index: 1397231 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.3951. Min Act: -0.1700

Data Index: 1570228 (Python Code)

Max Activating Token Index: 344

Text #4

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.3326. Min Act: -0.1700

Data Index: 1496617 (Python Code)

Max Activating Token Index: 753

Text #5

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.3639. Min Act: -0.1700

Data Index: 1391289 (Python Code)

Max Activating Token Index: 366

Text #6

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.2701. Min Act: -0.1700

Data Index: 1645823 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.3014. Min Act: -0.1700

Data Index: 1518522 (Python Code)

Max Activating Token Index: 621

Text #8

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.2076. Min Act: -0.1700

Data Index: 1389195 (Python Code)

Max Activating Token Index: 728

Text #9

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.2701. Min Act: -0.1700

Data Index: 1395063 (Python Code)

Max Activating Token Index: 498

Text #10

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.2389. Min Act: -0.1700

Data Index: 1515618 (Python Code)

Max Activating Token Index: 592

Text #11

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.1764. Min Act: -0.1700

Data Index: 1586084 (Python Code)

Max Activating Token Index: 366

Text #12

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.1451. Min Act: -0.1700

Data Index: 1456025 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.0826. Min Act: -0.1700

Data Index: 1380233 (Python Code)

Max Activating Token Index: 470

Text #14

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.0826. Min Act: -0.1700

Data Index: 1573208 (Python Code)

Max Activating Token Index: 771

Text #15

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.1139. Min Act: -0.1700

Data Index: 1523303 (Python Code)

Max Activating Token Index: 632

Text #16

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.1139. Min Act: -0.1700

Data Index: 1594864 (Python Code)

Max Activating Token Index: 365

Text #17

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.0514. Min Act: -0.1700

Data Index: 1650203 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.0201. Min Act: -0.1700

Data Index: 1519765 (Python Code)

Max Activating Token Index: 489

Text #19

Max Range: 5.7701. Min Range: -5.7701

Max Act: 5.0201. Min Act: -0.1700

Data Index: 1406634 (Python Code)

Max Activating Token Index: 910