Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1411 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.3866. Min Act: -0.1700
Data Index: 1415704 (Python Code)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.3866. Min Act: -0.1700
Data Index: 1524893 (Python Code)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.3554. Min Act: -0.1699
Data Index: 1414763 (Python Code)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.2616. Min Act: -0.1700
Data Index: 1529824 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.2304. Min Act: -0.1697
Data Index: 1560402 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.2304. Min Act: -0.1700
Data Index: 1549308 (Python Code)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.2304. Min Act: -0.1699
Data Index: 1470801 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.1991. Min Act: -0.1700
Data Index: 1556564 (Python Code)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.1991. Min Act: -0.1700
Data Index: 1392174 (Python Code)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.1991. Min Act: -0.1700
Data Index: 1508208 (Python Code)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.1366. Min Act: -0.1700
Data Index: 1653860 (Python Code)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.1678. Min Act: -0.1699
Data Index: 1548651 (Python Code)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1444297 (Python Code)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1562633 (Python Code)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1060260 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.0115. Min Act: -0.1700
Data Index: 901783 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.0741. Min Act: -0.1700
Data Index: 1459383 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.1053. Min Act: -0.1700
Data Index: 1513672 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.0428. Min Act: -0.1700
Data Index: 1431889 (Python Code)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3866. Min Range: -4.3866
Max Act: 4.0741. Min Act: -0.1700
Data Index: 1486759 (Python Code)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19