Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1440 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1686. Min Range: -4.1686

Max Act: 4.1686. Min Act: -0.1700

Data Index: 540210 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 4.1686. Min Range: -4.1686

Max Act: 4.1600. Min Act: -0.1700

Data Index: 51408 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 4.1686. Min Range: -4.1686

Max Act: 4.0044. Min Act: -0.1699

Data Index: 1042761 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.9215. Min Act: -0.1697

Data Index: 1517101 (Python Code)

Max Activating Token Index: 860

Text #4

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.8249. Min Act: -0.1700

Data Index: 1392918 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7808. Min Act: -0.1699

Data Index: 1371610 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7952. Min Act: -0.1700

Data Index: 1373033 (Python Code)

Max Activating Token Index: 986

Text #7

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7537. Min Act: -0.1690

Data Index: 1480190 (Python Code)

Max Activating Token Index: 337

Text #8

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7517. Min Act: -0.1700

Data Index: 1376242 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7314. Min Act: -0.1700

Data Index: 293901 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6927. Min Act: -0.1700

Data Index: 1479925 (Python Code)

Max Activating Token Index: 150

Text #11

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6876. Min Act: -0.1700

Data Index: 1549586 (Python Code)

Max Activating Token Index: 964

Text #12

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7304. Min Act: -0.1700

Data Index: 1383425 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7170. Min Act: -0.1698

Data Index: 1553794 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7299. Min Act: -0.1700

Data Index: 1469790 (Python Code)

Max Activating Token Index: 837

Text #15

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6838. Min Act: -0.1700

Data Index: 527907 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7511. Min Act: -0.1700

Data Index: 1354128 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.7021. Min Act: -0.1700

Data Index: 104876 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6582. Min Act: -0.1695

Data Index: 1473495 (Python Code)

Max Activating Token Index: 652

Text #19

Max Range: 4.1686. Min Range: -4.1686

Max Act: 3.6455. Min Act: -0.1700

Data Index: 1443667 (Python Code)

Max Activating Token Index: 592