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

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

Neuron 587 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: 5.2242. Min Range: -5.2242

Max Act: 5.2242. Min Act: -0.1699

Data Index: 1428300 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.1797. Min Act: -0.1700

Data Index: 1546696 (Python Code)

Max Activating Token Index: 777

Text #2

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.1573. Min Act: -0.1700

Data Index: 1501497 (Python Code)

Max Activating Token Index: 618

Text #3

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.1065. Min Act: -0.1700

Data Index: 1551635 (Python Code)

Max Activating Token Index: 453

Text #4

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.1153. Min Act: -0.1700

Data Index: 1559773 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0883. Min Act: -0.1699

Data Index: 1433524 (Python Code)

Max Activating Token Index: 386

Text #6

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0856. Min Act: -0.1700

Data Index: 1445184 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0660. Min Act: -0.1700

Data Index: 1468601 (Python Code)

Max Activating Token Index: 486

Text #8

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0160. Min Act: -0.1700

Data Index: 1497976 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0590. Min Act: -0.1700

Data Index: 1373227 (Python Code)

Max Activating Token Index: 190

Text #10

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0352. Min Act: -0.1700

Data Index: 1365717 (Python Code)

Max Activating Token Index: 239

Text #11

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0368. Min Act: -0.1700

Data Index: 1457073 (Python Code)

Max Activating Token Index: 826

Text #12

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0276. Min Act: -0.1700

Data Index: 1569978 (Python Code)

Max Activating Token Index: 569

Text #13

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0205. Min Act: -0.1700

Data Index: 1585028 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 5.2242. Min Range: -5.2242

Max Act: 5.0333. Min Act: -0.1700

Data Index: 1640555 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 5.2242. Min Range: -5.2242

Max Act: 4.9998. Min Act: -0.1700

Data Index: 1426562 (Python Code)

Max Activating Token Index: 270

Text #16

Max Range: 5.2242. Min Range: -5.2242

Max Act: 4.9820. Min Act: -0.1700

Data Index: 1455779 (Python Code)

Max Activating Token Index: 1018

Text #17

Max Range: 5.2242. Min Range: -5.2242

Max Act: 4.9986. Min Act: -0.1700

Data Index: 1397188 (Python Code)

Max Activating Token Index: 600

Text #18

Max Range: 5.2242. Min Range: -5.2242

Max Act: 4.9775. Min Act: -0.1700

Data Index: 1502277 (Python Code)

Max Activating Token Index: 766

Text #19

Max Range: 5.2242. Min Range: -5.2242

Max Act: 4.9885. Min Act: -0.1700

Data Index: 1434350 (Python Code)

Max Activating Token Index: 748