Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 185 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.7178. Min Act: -0.1700
Data Index: 1498623 (Python Code)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.6538. Min Act: -0.1700
Data Index: 1383957 (Python Code)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.6698. Min Act: -0.1700
Data Index: 1366706 (Python Code)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5895. Min Act: -0.1700
Data Index: 293658 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5734. Min Act: -0.1700
Data Index: 1655231 (Python Code)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5572. Min Act: -0.1700
Data Index: 1650237 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5572. Min Act: -0.1700
Data Index: 518386 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5411. Min Act: -0.1700
Data Index: 1591328 (Python Code)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5249. Min Act: -0.1700
Data Index: 1513533 (Python Code)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5249. Min Act: -0.1700
Data Index: 1411851 (Python Code)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5249. Min Act: -0.1700
Data Index: 1121843 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.4926. Min Act: -0.1700
Data Index: 1431871 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5087. Min Act: -0.1700
Data Index: 1560361 (Python Code)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5087. Min Act: -0.1700
Data Index: 1441121 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5087. Min Act: -0.1700
Data Index: 1380044 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.4926. Min Act: -0.1700
Data Index: 1596753 (Python Code)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.4926. Min Act: -0.1700
Data Index: 1620821 (Python Code)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.5087. Min Act: -0.1700
Data Index: 1643659 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.4926. Min Act: -0.1700
Data Index: 1642780 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7178. Min Range: -2.7178
Max Act: 2.4763. Min Act: -0.1700
Data Index: 1559841 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19