Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 10 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 3.0813. Min Range: -3.0813
Max Act: 3.0813. Min Act: -0.1700
Data Index: 982185 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.6202. Min Act: -0.1700
Data Index: 1490192 (Python Code)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.5719. Min Act: -0.1698
Data Index: 1450218 (Python Code)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.5719. Min Act: -0.1663
Data Index: 1433529 (Python Code)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.5073. Min Act: -0.1700
Data Index: 850805 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.5073. Min Act: -0.1700
Data Index: 1639712 (Python Code)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.5235. Min Act: -0.1700
Data Index: 1573761 (Python Code)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4911. Min Act: -0.1700
Data Index: 1494428 (Python Code)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4749. Min Act: -0.1700
Data Index: 989323 (C4 (Web Text))
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4911. Min Act: -0.1700
Data Index: 83665 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4424. Min Act: -0.1700
Data Index: 1535375 (Python Code)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4261. Min Act: -0.1700
Data Index: 1590856 (Python Code)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4261. Min Act: -0.1700
Data Index: 1649887 (Python Code)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4261. Min Act: -0.1700
Data Index: 1366277 (Python Code)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4261. Min Act: -0.1700
Data Index: 1530320 (Python Code)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4261. Min Act: -0.1700
Data Index: 1633456 (Python Code)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4261. Min Act: -0.1700
Data Index: 231891 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4098. Min Act: -0.1699
Data Index: 186112 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4261. Min Act: -0.1699
Data Index: 51663 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0813. Min Range: -3.0813
Max Act: 2.4424. Min Act: -0.1700
Data Index: 1454603 (Python Code)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19