Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 313 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.5251. Min Act: -0.1700
Data Index: 1553591 (Python Code)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.5089. Min Act: -0.1700
Data Index: 560688 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.5089. Min Act: -0.1700
Data Index: 1482224 (Python Code)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4765. Min Act: -0.1700
Data Index: 1431693 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4927. Min Act: -0.1700
Data Index: 1492388 (Python Code)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4927. Min Act: -0.1700
Data Index: 1524407 (Python Code)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4765. Min Act: -0.1700
Data Index: 1413965 (Python Code)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4602. Min Act: -0.1700
Data Index: 1488486 (Python Code)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4765. Min Act: -0.1700
Data Index: 1465480 (Python Code)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4602. Min Act: -0.1700
Data Index: 1455991 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4765. Min Act: -0.1700
Data Index: 1516664 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4765. Min Act: -0.1700
Data Index: 1623549 (Python Code)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4765. Min Act: -0.1700
Data Index: 1612267 (Python Code)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4765. Min Act: -0.1700
Data Index: 1580025 (Python Code)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4765. Min Act: -0.1700
Data Index: 1562201 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4602. Min Act: -0.1700
Data Index: 1430543 (Python Code)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4440. Min Act: -0.1700
Data Index: 1425462 (Python Code)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4602. Min Act: -0.1700
Data Index: 1393287 (Python Code)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4602. Min Act: -0.1700
Data Index: 1448950 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5251. Min Range: -2.5251
Max Act: 2.4602. Min Act: -0.1700
Data Index: 1454005 (Python Code)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19