Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1379 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.8919. Min Act: -0.1700
Data Index: 1499901 (Python Code)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.9077. Min Act: -0.1700
Data Index: 1378260 (Python Code)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.8760. Min Act: -0.1700
Data Index: 1628304 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.8601. Min Act: -0.1700
Data Index: 1420594 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.8601. Min Act: -0.1700
Data Index: 1479673 (Python Code)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.8442. Min Act: -0.1700
Data Index: 1473413 (Python Code)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.8442. Min Act: -0.1700
Data Index: 1404039 (Python Code)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.8442. Min Act: -0.1700
Data Index: 1479037 (Python Code)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.8283. Min Act: -0.1700
Data Index: 1411617 (Python Code)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7965. Min Act: -0.1700
Data Index: 1379887 (Python Code)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.8124. Min Act: -0.1700
Data Index: 1580297 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7646. Min Act: -0.1700
Data Index: 1654253 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7646. Min Act: -0.1700
Data Index: 1528148 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7805. Min Act: -0.1700
Data Index: 1460913 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7805. Min Act: -0.1700
Data Index: 1614315 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7805. Min Act: -0.1700
Data Index: 1501853 (Python Code)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7805. Min Act: -0.1700
Data Index: 1427846 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7805. Min Act: -0.1700
Data Index: 1424981 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7805. Min Act: -0.1700
Data Index: 1468849 (Python Code)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9077. Min Range: -2.9077
Max Act: 2.7646. Min Act: -0.1700
Data Index: 1472821 (Python Code)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19