Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2001 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0827. Min Range: -3.0827
Max Act: 3.0827. Min Act: -0.1700
Data Index: 1419058 (Python Code)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0827. Min Range: -3.0827
Max Act: 3.0354. Min Act: -0.1700
Data Index: 1511834 (Python Code)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0827. Min Range: -3.0827
Max Act: 3.0038. Min Act: -0.1700
Data Index: 1532996 (Python Code)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0827. Min Range: -3.0827
Max Act: 3.0038. Min Act: -0.1700
Data Index: 1631292 (Python Code)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9880. Min Act: -0.1700
Data Index: 1114975 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9880. Min Act: -0.1700
Data Index: 1510321 (Python Code)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9880. Min Act: -0.1700
Data Index: 915850 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9722. Min Act: -0.1700
Data Index: 1538428 (Python Code)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9563. Min Act: -0.1700
Data Index: 1309150 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9405. Min Act: -0.1700
Data Index: 1373785 (Python Code)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9563. Min Act: -0.1700
Data Index: 1468736 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9563. Min Act: -0.1700
Data Index: 1509508 (Python Code)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9088. Min Act: -0.1700
Data Index: 1308801 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.9088. Min Act: -0.1700
Data Index: 1621727 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.8929. Min Act: -0.1700
Data Index: 631703 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.8771. Min Act: -0.1700
Data Index: 245558 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.8929. Min Act: -0.1700
Data Index: 1544881 (Python Code)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.8929. Min Act: -0.1700
Data Index: 1446105 (Python Code)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.8929. Min Act: -0.1700
Data Index: 1457692 (Python Code)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0827. Min Range: -3.0827
Max Act: 2.8771. Min Act: -0.1700
Data Index: 114434 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19