Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2047 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.8780. Min Act: -0.1700
Data Index: 1462821 (Python Code)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.6903. Min Act: -0.1700
Data Index: 1562775 (Python Code)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.6903. Min Act: -0.1700
Data Index: 1556987 (Python Code)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.6903. Min Act: -0.1700
Data Index: 1645420 (Python Code)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.6277. Min Act: -0.1700
Data Index: 1395022 (Python Code)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.6590. Min Act: -0.1700
Data Index: 1404491 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1608490 (Python Code)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.6590. Min Act: -0.1700
Data Index: 1611929 (Python Code)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1622363 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1559086 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1488627 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.6277. Min Act: -0.1700
Data Index: 1529358 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1503597 (Python Code)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5651. Min Act: -0.1700
Data Index: 1578990 (Python Code)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5651. Min Act: -0.1700
Data Index: 1381472 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5338. Min Act: -0.1700
Data Index: 1620634 (Python Code)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1414676 (Python Code)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5651. Min Act: -0.1700
Data Index: 1448909 (Python Code)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5964. Min Act: -0.1700
Data Index: 1443679 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8780. Min Range: -3.8780
Max Act: 3.5651. Min Act: -0.1700
Data Index: 1585554 (Python Code)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19