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

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

Neuron 1534 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: 4.8544. Min Range: -4.8544

Max Act: 4.8544. Min Act: -0.1700

Data Index: 1494086 (Python Code)

Max Activating Token Index: 714

Text #1

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.7603. Min Act: -0.1692

Data Index: 1509658 (Python Code)

Max Activating Token Index: 408

Text #2

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.6612. Min Act: -0.1692

Data Index: 1506401 (Python Code)

Max Activating Token Index: 132

Text #3

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.6477. Min Act: -0.1700

Data Index: 1562898 (Python Code)

Max Activating Token Index: 903

Text #4

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.6655. Min Act: -0.1700

Data Index: 1519729 (Python Code)

Max Activating Token Index: 864

Text #5

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.6123. Min Act: -0.1700

Data Index: 1595385 (Python Code)

Max Activating Token Index: 930

Text #6

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.5904. Min Act: -0.1700

Data Index: 1467366 (Python Code)

Max Activating Token Index: 376

Text #7

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.6032. Min Act: -0.1699

Data Index: 1514636 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.5795. Min Act: -0.1700

Data Index: 1361263 (Python Code)

Max Activating Token Index: 892

Text #9

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.5348. Min Act: -0.1699

Data Index: 1561272 (Python Code)

Max Activating Token Index: 648

Text #10

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.5461. Min Act: -0.1700

Data Index: 1644541 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.5120. Min Act: -0.1693

Data Index: 1653331 (Python Code)

Max Activating Token Index: 154

Text #12

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.5137. Min Act: -0.1699

Data Index: 1385130 (Python Code)

Max Activating Token Index: 171

Text #13

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.4747. Min Act: -0.1700

Data Index: 1616181 (Python Code)

Max Activating Token Index: 447

Text #14

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.4616. Min Act: -0.1700

Data Index: 1547687 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.4619. Min Act: -0.1700

Data Index: 1575004 (Python Code)

Max Activating Token Index: 443

Text #16

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.4370. Min Act: -0.1693

Data Index: 1389893 (Python Code)

Max Activating Token Index: 558

Text #17

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.4247. Min Act: -0.1699

Data Index: 1594979 (Python Code)

Max Activating Token Index: 871

Text #18

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.4316. Min Act: -0.1699

Data Index: 1455411 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 4.8544. Min Range: -4.8544

Max Act: 4.4535. Min Act: -0.1700

Data Index: 1634926 (Python Code)

Max Activating Token Index: 505