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

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

Neuron 1612 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: 3.2321. Min Range: -3.2321

Max Act: 3.2321. Min Act: -0.1700

Data Index: 291514 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1534. Min Act: -0.1700

Data Index: 221515 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1849. Min Act: -0.1700

Data Index: 1485853 (Python Code)

Max Activating Token Index: 628

Text #3

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1534. Min Act: -0.1700

Data Index: 246693 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1534. Min Act: -0.1700

Data Index: 1534035 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1219. Min Act: -0.1700

Data Index: 1377911 (Python Code)

Max Activating Token Index: 132

Text #6

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1219. Min Act: -0.1700

Data Index: 1470917 (Python Code)

Max Activating Token Index: 1017

Text #7

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1061. Min Act: -0.1700

Data Index: 492408 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1219. Min Act: -0.1700

Data Index: 1434158 (Python Code)

Max Activating Token Index: 552

Text #9

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0904. Min Act: -0.1700

Data Index: 1601313 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0746. Min Act: -0.1700

Data Index: 1623907 (Python Code)

Max Activating Token Index: 994

Text #11

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.1061. Min Act: -0.1700

Data Index: 1600366 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0272. Min Act: -0.1700

Data Index: 1474281 (Python Code)

Max Activating Token Index: 452

Text #13

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0588. Min Act: -0.1700

Data Index: 1523473 (Python Code)

Max Activating Token Index: 918

Text #14

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0904. Min Act: -0.1700

Data Index: 1526197 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0588. Min Act: -0.1700

Data Index: 1463387 (Python Code)

Max Activating Token Index: 278

Text #16

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0746. Min Act: -0.1700

Data Index: 1406200 (Python Code)

Max Activating Token Index: 777

Text #17

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0746. Min Act: -0.1700

Data Index: 1424777 (Python Code)

Max Activating Token Index: 908

Text #18

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0272. Min Act: -0.1700

Data Index: 1421476 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 3.2321. Min Range: -3.2321

Max Act: 3.0746. Min Act: -0.1700

Data Index: 1280487 (C4 (Web Text))

Max Activating Token Index: 340