Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1922 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.3640. Min Act: -0.1700
Data Index: 1514175 (Python Code)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.1765. Min Act: -0.1700
Data Index: 1273556 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.1140. Min Act: -0.1700
Data Index: 1556637 (Python Code)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0827. Min Act: -0.1700
Data Index: 678115 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0514. Min Act: -0.1700
Data Index: 1570119 (Python Code)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0827. Min Act: -0.1700
Data Index: 1384043 (Python Code)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0827. Min Act: -0.1700
Data Index: 1481253 (Python Code)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0827. Min Act: -0.1700
Data Index: 1598388 (Python Code)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0827. Min Act: -0.1700
Data Index: 1398320 (Python Code)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0202. Min Act: -0.1700
Data Index: 1607072 (Python Code)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3640. Min Range: -4.3640
Max Act: 3.9889. Min Act: -0.1700
Data Index: 1453974 (Python Code)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0202. Min Act: -0.1700
Data Index: 1581735 (Python Code)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0827. Min Act: -0.1700
Data Index: 1447413 (Python Code)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0514. Min Act: -0.1700
Data Index: 1369883 (Python Code)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3640. Min Range: -4.3640
Max Act: 3.9889. Min Act: -0.1700
Data Index: 1436980 (Python Code)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0202. Min Act: -0.1700
Data Index: 1462735 (Python Code)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0202. Min Act: -0.1700
Data Index: 1387006 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0202. Min Act: -0.1700
Data Index: 1426863 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0514. Min Act: -0.1700
Data Index: 1527951 (Python Code)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3640. Min Range: -4.3640
Max Act: 4.0202. Min Act: -0.1700
Data Index: 1616059 (Python Code)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19