Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1973 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.4851. Min Act: -0.1700
Data Index: 99744 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.4527. Min Act: -0.1700
Data Index: 1313016 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.4364. Min Act: -0.1700
Data Index: 1519252 (Python Code)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.4364. Min Act: -0.1700
Data Index: 1649953 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.4201. Min Act: -0.1700
Data Index: 758937 (C4 (Web Text))
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.4039. Min Act: -0.1700
Data Index: 937054 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.4039. Min Act: -0.1700
Data Index: 1482748 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3712. Min Act: -0.1700
Data Index: 627923 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3875. Min Act: -0.1700
Data Index: 1639389 (Python Code)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3875. Min Act: -0.1700
Data Index: 1493565 (Python Code)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3875. Min Act: -0.1700
Data Index: 1496591 (Python Code)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3875. Min Act: -0.1700
Data Index: 1586514 (Python Code)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.4039. Min Act: -0.1700
Data Index: 831356 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3712. Min Act: -0.1700
Data Index: 641938 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3875. Min Act: -0.1700
Data Index: 1319663 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3712. Min Act: -0.1700
Data Index: 1531663 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3875. Min Act: -0.1700
Data Index: 1654500 (Python Code)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3712. Min Act: -0.1700
Data Index: 1622080 (Python Code)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3712. Min Act: -0.1700
Data Index: 765645 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4851. Min Range: -2.4851
Max Act: 2.3548. Min Act: -0.1700
Data Index: 484046 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19