Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 61 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1813. Min Act: -0.1700
Data Index: 131114 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1970. Min Act: -0.1700
Data Index: 1517684 (Python Code)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1655. Min Act: -0.1700
Data Index: 1594398 (Python Code)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1340. Min Act: -0.1700
Data Index: 1401290 (Python Code)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1183. Min Act: -0.1700
Data Index: 1436434 (Python Code)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1183. Min Act: -0.1700
Data Index: 1487939 (Python Code)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1970. Min Act: -0.1700
Data Index: 364321 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1183. Min Act: -0.1700
Data Index: 1594825 (Python Code)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1025. Min Act: -0.1700
Data Index: 1434074 (Python Code)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.0867. Min Act: -0.1700
Data Index: 1525472 (Python Code)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1025. Min Act: -0.1700
Data Index: 1573689 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1025. Min Act: -0.1700
Data Index: 1327134 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1498. Min Act: -0.1700
Data Index: 693939 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.0867. Min Act: -0.1700
Data Index: 1554517 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.1025. Min Act: -0.1700
Data Index: 543060 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.0710. Min Act: -0.1700
Data Index: 1591623 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.0394. Min Act: -0.1700
Data Index: 1381574 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.0867. Min Act: -0.1700
Data Index: 1496496 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.0394. Min Act: -0.1700
Data Index: 1573365 (Python Code)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1970. Min Range: -3.1970
Max Act: 3.0394. Min Act: -0.1700
Data Index: 1446702 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19