Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1078 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.8659. Min Act: -0.1700
Data Index: 1633134 (Python Code)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.8341. Min Act: -0.1700
Data Index: 1451414 (Python Code)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.7545. Min Act: -0.1700
Data Index: 1609525 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.7065. Min Act: -0.1700
Data Index: 1526012 (Python Code)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.7225. Min Act: -0.1700
Data Index: 1457628 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6905. Min Act: -0.1700
Data Index: 1616826 (Python Code)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6745. Min Act: -0.1700
Data Index: 1461861 (Python Code)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6745. Min Act: -0.1700
Data Index: 1572684 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6745. Min Act: -0.1700
Data Index: 1590636 (Python Code)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6424. Min Act: -0.1700
Data Index: 1403828 (Python Code)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6585. Min Act: -0.1700
Data Index: 1473287 (Python Code)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6424. Min Act: -0.1699
Data Index: 1510280 (Python Code)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6424. Min Act: -0.1700
Data Index: 1390866 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6424. Min Act: -0.1700
Data Index: 1596805 (Python Code)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6424. Min Act: -0.1700
Data Index: 1630433 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6424. Min Act: -0.1700
Data Index: 1413543 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6585. Min Act: -0.1700
Data Index: 1656109 (Python Code)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6264. Min Act: -0.1700
Data Index: 1533115 (Python Code)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6264. Min Act: -0.1700
Data Index: 1510898 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8659. Min Range: -2.8659
Max Act: 2.6264. Min Act: -0.1700
Data Index: 1473623 (Python Code)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19