Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1385 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.6769. Min Act: -0.1700
Data Index: 1609627 (Python Code)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.7082. Min Act: -0.1700
Data Index: 1501399 (Python Code)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.7082. Min Act: -0.1700
Data Index: 1549879 (Python Code)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.6144. Min Act: -0.1700
Data Index: 1636818 (Python Code)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.5832. Min Act: -0.1700
Data Index: 1471251 (Python Code)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.5519. Min Act: -0.1700
Data Index: 1527081 (Python Code)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4894. Min Act: -0.1700
Data Index: 1460242 (Python Code)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4582. Min Act: -0.1700
Data Index: 1582405 (Python Code)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4269. Min Act: -0.1700
Data Index: 1364626 (Python Code)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4894. Min Act: -0.1700
Data Index: 1606989 (Python Code)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4582. Min Act: -0.1700
Data Index: 1417601 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4269. Min Act: -0.1700
Data Index: 1476852 (Python Code)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4269. Min Act: -0.1700
Data Index: 1488977 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4269. Min Act: -0.1700
Data Index: 1507518 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3956. Min Act: -0.1700
Data Index: 1375014 (Python Code)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4269. Min Act: -0.1700
Data Index: 1435333 (Python Code)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4269. Min Act: -0.1700
Data Index: 1434732 (Python Code)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3956. Min Act: -0.1700
Data Index: 1495498 (Python Code)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.4269. Min Act: -0.1700
Data Index: 1491853 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7082. Min Range: -4.7082
Max Act: 4.3956. Min Act: -0.1700
Data Index: 1454882 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #19