Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1043 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.7472. Min Act: -0.1696
Data Index: 1382003 (Python Code)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.7153. Min Act: -0.1700
Data Index: 1599251 (Python Code)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.6993. Min Act: -0.1700
Data Index: 1561161 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.6993. Min Act: -0.1699
Data Index: 1571564 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.6673. Min Act: -0.1700
Data Index: 1521550 (Python Code)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.6352. Min Act: -0.1676
Data Index: 1603125 (Python Code)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.6512. Min Act: -0.1700
Data Index: 1508756 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.6030. Min Act: -0.1700
Data Index: 1427482 (Python Code)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.6352. Min Act: -0.1699
Data Index: 1649330 (Python Code)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.6030. Min Act: -0.1700
Data Index: 1469248 (Python Code)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5869. Min Act: -0.1700
Data Index: 1394469 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5708. Min Act: -0.1699
Data Index: 1377827 (Python Code)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5869. Min Act: -0.1696
Data Index: 1482759 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5869. Min Act: -0.1697
Data Index: 1530840 (Python Code)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5869. Min Act: -0.1700
Data Index: 1644503 (Python Code)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5869. Min Act: -0.1698
Data Index: 1463004 (Python Code)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5547. Min Act: -0.1700
Data Index: 1473015 (Python Code)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5708. Min Act: -0.1700
Data Index: 1605970 (Python Code)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5708. Min Act: -0.1700
Data Index: 1368097 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7472. Min Range: -2.7472
Max Act: 2.5547. Min Act: -0.1700
Data Index: 1554428 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19