Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1206 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.6211. Min Act: -0.1700
Data Index: 523186 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.6372. Min Act: -0.1700
Data Index: 223806 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.6372. Min Act: -0.1700
Data Index: 1135585 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.6211. Min Act: -0.1700
Data Index: 1453421 (Python Code)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.6051. Min Act: -0.1700
Data Index: 1123733 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5890. Min Act: -0.1700
Data Index: 325835 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.6211. Min Act: -0.1700
Data Index: 1562905 (Python Code)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5728. Min Act: -0.1700
Data Index: 1121736 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5890. Min Act: -0.1700
Data Index: 528863 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5728. Min Act: -0.1700
Data Index: 1325763 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5728. Min Act: -0.1700
Data Index: 573288 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5728. Min Act: -0.1700
Data Index: 1011380 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5567. Min Act: -0.1700
Data Index: 1343012 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5244. Min Act: -0.1700
Data Index: 1496818 (Python Code)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5406. Min Act: -0.1700
Data Index: 1405916 (Python Code)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5244. Min Act: -0.1700
Data Index: 1490217 (Python Code)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5244. Min Act: -0.1700
Data Index: 1220015 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5406. Min Act: -0.1700
Data Index: 918586 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5406. Min Act: -0.1700
Data Index: 226764 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6372. Min Range: -2.6372
Max Act: 2.5244. Min Act: -0.1700
Data Index: 263976 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #19