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

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

Neuron 1644 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: 3.7325. Min Range: -3.7325

Max Act: 3.7325. Min Act: -0.1700

Data Index: 1580276 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.7207. Min Act: -0.1700

Data Index: 1577806 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.6004. Min Act: -0.1700

Data Index: 1385303 (Python Code)

Max Activating Token Index: 940

Text #3

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.5757. Min Act: -0.1700

Data Index: 1610012 (Python Code)

Max Activating Token Index: 662

Text #4

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.5307. Min Act: -0.1700

Data Index: 1477226 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.5068. Min Act: -0.1700

Data Index: 1651068 (Python Code)

Max Activating Token Index: 301

Text #6

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4735. Min Act: -0.1700

Data Index: 1424956 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4554. Min Act: -0.1700

Data Index: 1475346 (Python Code)

Max Activating Token Index: 896

Text #8

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4436. Min Act: -0.1700

Data Index: 1408527 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4593. Min Act: -0.1700

Data Index: 1410214 (Python Code)

Max Activating Token Index: 507

Text #10

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4639. Min Act: -0.1700

Data Index: 1577182 (Python Code)

Max Activating Token Index: 427

Text #11

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4358. Min Act: -0.1700

Data Index: 1514304 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4461. Min Act: -0.1700

Data Index: 1413969 (Python Code)

Max Activating Token Index: 510

Text #13

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4170. Min Act: -0.1700

Data Index: 1485360 (Python Code)

Max Activating Token Index: 484

Text #14

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4111. Min Act: -0.1700

Data Index: 1643597 (Python Code)

Max Activating Token Index: 1000

Text #15

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4118. Min Act: -0.1700

Data Index: 1506261 (Python Code)

Max Activating Token Index: 611

Text #16

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.3930. Min Act: -0.1700

Data Index: 1536591 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4045. Min Act: -0.1700

Data Index: 1432765 (Python Code)

Max Activating Token Index: 754

Text #18

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.4029. Min Act: -0.1700

Data Index: 1597332 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 3.7325. Min Range: -3.7325

Max Act: 3.3582. Min Act: -0.1700

Data Index: 1450889 (Python Code)

Max Activating Token Index: 816