Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 68 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.8004. Min Act: -0.1699
Data Index: 1622914 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.7379. Min Act: -0.1700
Data Index: 1472129 (Python Code)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.6442. Min Act: -0.1699
Data Index: 1609817 (Python Code)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.5817. Min Act: -0.1699
Data Index: 1610636 (Python Code)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.5192. Min Act: -0.1699
Data Index: 1472389 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.5035. Min Act: -0.1678
Data Index: 1479788 (Python Code)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.4723. Min Act: -0.1698
Data Index: 1497313 (Python Code)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.4410. Min Act: -0.1700
Data Index: 1399452 (Python Code)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.3941. Min Act: -0.1700
Data Index: 1558415 (Python Code)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.3785. Min Act: -0.1700
Data Index: 1473592 (Python Code)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.3941. Min Act: -0.1700
Data Index: 1597413 (Python Code)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.3629. Min Act: -0.1699
Data Index: 1443037 (Python Code)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.3473. Min Act: -0.1700
Data Index: 1441284 (Python Code)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.3004. Min Act: -0.1700
Data Index: 1489476 (Python Code)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.3004. Min Act: -0.1700
Data Index: 1586436 (Python Code)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.3004. Min Act: -0.1699
Data Index: 1442406 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.2379. Min Act: -0.1699
Data Index: 1571804 (Python Code)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.2535. Min Act: -0.1650
Data Index: 1635142 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.2691. Min Act: -0.1700
Data Index: 1541604 (Python Code)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8004. Min Range: -4.8004
Max Act: 4.3004. Min Act: -0.1699
Data Index: 1461175 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19