Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2013 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0449. Min Range: -3.0449
Max Act: 3.0449. Min Act: -0.1700
Data Index: 1631859 (Python Code)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.9816. Min Act: -0.1700
Data Index: 1395071 (Python Code)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1487831 (Python Code)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.9183. Min Act: -0.1700
Data Index: 1399899 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.9342. Min Act: -0.1700
Data Index: 1614982 (Python Code)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.9342. Min Act: -0.1700
Data Index: 1406204 (Python Code)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.9024. Min Act: -0.1700
Data Index: 1479623 (Python Code)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8707. Min Act: -0.1700
Data Index: 1613566 (Python Code)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8548. Min Act: -0.1700
Data Index: 1494022 (Python Code)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8707. Min Act: -0.1700
Data Index: 1414525 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8389. Min Act: -0.1700
Data Index: 1521185 (Python Code)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8389. Min Act: -0.1700
Data Index: 1386006 (Python Code)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8389. Min Act: -0.1700
Data Index: 1638198 (Python Code)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8548. Min Act: -0.1700
Data Index: 1449619 (Python Code)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8389. Min Act: -0.1700
Data Index: 1419792 (Python Code)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8548. Min Act: -0.1700
Data Index: 1420665 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8707. Min Act: -0.1700
Data Index: 1533296 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8389. Min Act: -0.1700
Data Index: 1515152 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8707. Min Act: -0.1700
Data Index: 1610393 (Python Code)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0449. Min Range: -3.0449
Max Act: 2.8389. Min Act: -0.1700
Data Index: 1530857 (Python Code)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19