Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1311 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.7656. Min Act: -0.1700

Data Index: 1578492 (Python Code)

Max Activating Token Index: 441

Text #1

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.7344. Min Act: -0.1700

Data Index: 1498132 (Python Code)

Max Activating Token Index: 436

Text #2

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.6406. Min Act: -0.1700

Data Index: 1446543 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.6406. Min Act: -0.1700

Data Index: 1399810 (Python Code)

Max Activating Token Index: 618

Text #4

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.6406. Min Act: -0.1700

Data Index: 1378306 (Python Code)

Max Activating Token Index: 551

Text #5

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.6719. Min Act: -0.1700

Data Index: 1380734 (Python Code)

Max Activating Token Index: 523

Text #6

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.6094. Min Act: -0.1700

Data Index: 1367412 (Python Code)

Max Activating Token Index: 290

Text #7

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.7031. Min Act: -0.1700

Data Index: 1385272 (Python Code)

Max Activating Token Index: 473

Text #8

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.6094. Min Act: -0.1700

Data Index: 1466823 (Python Code)

Max Activating Token Index: 551

Text #9

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.6094. Min Act: -0.1700

Data Index: 1654899 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.6719. Min Act: -0.1700

Data Index: 1554678 (Python Code)

Max Activating Token Index: 672

Text #11

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.5781. Min Act: -0.1700

Data Index: 1466317 (Python Code)

Max Activating Token Index: 749

Text #12

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.6094. Min Act: -0.1700

Data Index: 1595467 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.5469. Min Act: -0.1700

Data Index: 1520284 (Python Code)

Max Activating Token Index: 714

Text #14

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.5781. Min Act: -0.1700

Data Index: 1475459 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.5781. Min Act: -0.1700

Data Index: 1631948 (Python Code)

Max Activating Token Index: 284

Text #16

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.5781. Min Act: -0.1700

Data Index: 1519898 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.4844. Min Act: -0.1700

Data Index: 1511887 (Python Code)

Max Activating Token Index: 472

Text #18

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.5781. Min Act: -0.1700

Data Index: 1577706 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 5.7656. Min Range: -5.7656

Max Act: 5.5469. Min Act: -0.1700

Data Index: 1550932 (Python Code)

Max Activating Token Index: 629