Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 668 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2995. Min Act: -0.1700
Data Index: 512939 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2995. Min Act: -0.1700
Data Index: 647036 (C4 (Web Text))
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2995. Min Act: -0.1700
Data Index: 173426 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2830. Min Act: -0.1700
Data Index: 19370 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2830. Min Act: -0.1700
Data Index: 103627 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2665. Min Act: -0.1700
Data Index: 1425263 (Python Code)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2335. Min Act: -0.1700
Data Index: 790129 (C4 (Web Text))
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2335. Min Act: -0.1700
Data Index: 410815 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2500. Min Act: -0.1700
Data Index: 785441 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2335. Min Act: -0.1700
Data Index: 1193582 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2170. Min Act: -0.1700
Data Index: 1131809 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2004. Min Act: -0.1700
Data Index: 16173 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2004. Min Act: -0.1700
Data Index: 358636 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.2004. Min Act: -0.1700
Data Index: 1161280 (C4 (Web Text))
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.1838. Min Act: -0.1700
Data Index: 89410 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.1672. Min Act: -0.1700
Data Index: 90510 (C4 (Web Text))
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.1672. Min Act: -0.1700
Data Index: 258858 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.1838. Min Act: -0.1700
Data Index: 353233 (C4 (Web Text))
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.1505. Min Act: -0.1700
Data Index: 507690 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2995. Min Range: -2.2995
Max Act: 2.1505. Min Act: -0.1700
Data Index: 1239831 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19