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

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

Neuron 893 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.4622. Min Act: -0.1700

Data Index: 1454121 (Python Code)

Max Activating Token Index: 432

Text #1

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.4308. Min Act: -0.1700

Data Index: 1617509 (Python Code)

Max Activating Token Index: 273

Text #2

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.4151. Min Act: -0.1700

Data Index: 1656364 (Python Code)

Max Activating Token Index: 600

Text #3

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.4151. Min Act: -0.1700

Data Index: 1651896 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.4151. Min Act: -0.1700

Data Index: 1513700 (Python Code)

Max Activating Token Index: 81

Text #5

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.4151. Min Act: -0.1700

Data Index: 1646561 (Python Code)

Max Activating Token Index: 498

Text #6

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.4151. Min Act: -0.1700

Data Index: 1601010 (Python Code)

Max Activating Token Index: 109

Text #7

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3994. Min Act: -0.1700

Data Index: 1539340 (Python Code)

Max Activating Token Index: 498

Text #8

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3994. Min Act: -0.1700

Data Index: 1521429 (Python Code)

Max Activating Token Index: 629

Text #9

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.4151. Min Act: -0.1700

Data Index: 1589819 (Python Code)

Max Activating Token Index: 473

Text #10

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3994. Min Act: -0.1700

Data Index: 1647685 (Python Code)

Max Activating Token Index: 543

Text #11

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3681. Min Act: -0.1700

Data Index: 1476733 (Python Code)

Max Activating Token Index: 527

Text #12

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3838. Min Act: -0.1700

Data Index: 1585996 (Python Code)

Max Activating Token Index: 463

Text #13

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3681. Min Act: -0.1700

Data Index: 1362583 (Python Code)

Max Activating Token Index: 487

Text #14

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3681. Min Act: -0.1700

Data Index: 1579355 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3524. Min Act: -0.1700

Data Index: 1512634 (Python Code)

Max Activating Token Index: 404

Text #16

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3524. Min Act: -0.1700

Data Index: 1601412 (Python Code)

Max Activating Token Index: 506

Text #17

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3524. Min Act: -0.1700

Data Index: 1620323 (Python Code)

Max Activating Token Index: 341

Text #18

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3210. Min Act: -0.1699

Data Index: 1471203 (Python Code)

Max Activating Token Index: 977

Text #19

Max Range: 3.4622. Min Range: -3.4622

Max Act: 3.3367. Min Act: -0.1700

Data Index: 1514007 (Python Code)

Max Activating Token Index: 273