Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3703 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.0919. Min Range: -1.0919
Max Act: 1.0919. Min Act: -0.1700
Data Index: 1059124 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.9528. Min Act: -0.1700
Data Index: 1008851 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.9356. Min Act: -0.1700
Data Index: 2398353 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.9012. Min Act: -0.1699
Data Index: 7605919 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8841. Min Act: -0.1678
Data Index: 4087993 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.9012. Min Act: -0.1700
Data Index: 4596476 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8671. Min Act: -0.1700
Data Index: 5444668 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8501. Min Act: -0.1700
Data Index: 307941 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8501. Min Act: -0.1700
Data Index: 1608085 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8501. Min Act: -0.1700
Data Index: 7253255 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8501. Min Act: -0.1700
Data Index: 7266375 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8332. Min Act: -0.1700
Data Index: 5421359 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8332. Min Act: -0.1699
Data Index: 3833427 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8332. Min Act: -0.1700
Data Index: 1716678 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8332. Min Act: -0.1700
Data Index: 845591 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8332. Min Act: -0.1700
Data Index: 6943658 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8163. Min Act: -0.1700
Data Index: 8272993 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8163. Min Act: -0.1700
Data Index: 2370042 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8163. Min Act: -0.1700
Data Index: 5682919 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0919. Min Range: -1.0919
Max Act: 0.8163. Min Act: -0.1700
Data Index: 3967578 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19