Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1942 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0606. Min Range: -3.0606
Max Act: 3.0606. Min Act: -0.1700
Data Index: 1455867 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0606. Min Range: -3.0606
Max Act: 3.0606. Min Act: -0.1700
Data Index: 1206665 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0606. Min Range: -3.0606
Max Act: 3.0133. Min Act: -0.1700
Data Index: 1397728 (Python Code)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9974. Min Act: -0.1700
Data Index: 1469057 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9974. Min Act: -0.1700
Data Index: 1522842 (Python Code)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9974. Min Act: -0.1700
Data Index: 1389483 (Python Code)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0606. Min Range: -3.0606
Max Act: 3.0133. Min Act: -0.1700
Data Index: 1521622 (Python Code)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9974. Min Act: -0.1700
Data Index: 1380836 (Python Code)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9816. Min Act: -0.1700
Data Index: 1576542 (Python Code)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9816. Min Act: -0.1700
Data Index: 1430438 (Python Code)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9974. Min Act: -0.1700
Data Index: 1499250 (Python Code)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1554232 (Python Code)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9500. Min Act: -0.1700
Data Index: 1507861 (Python Code)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1546722 (Python Code)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9500. Min Act: -0.1700
Data Index: 1524473 (Python Code)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1605418 (Python Code)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1431233 (Python Code)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9500. Min Act: -0.1700
Data Index: 1558503 (Python Code)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9500. Min Act: -0.1700
Data Index: 1558922 (Python Code)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0606. Min Range: -3.0606
Max Act: 2.9658. Min Act: -0.1700
Data Index: 1597051 (Python Code)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #19