Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4694 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.3561. Min Act: -0.1699
Data Index: 2616962 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3561. Min Range: -5.3561
Max Act: 5.1686. Min Act: -0.1700
Data Index: 1825619 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.9811. Min Act: -0.1700
Data Index: 4549606 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.9186. Min Act: -0.1700
Data Index: 1657069 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.9811. Min Act: -0.1700
Data Index: 1003777 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.9186. Min Act: -0.1700
Data Index: 4749353 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.9186. Min Act: -0.1700
Data Index: 7614700 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8561. Min Act: -0.1700
Data Index: 265506 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8874. Min Act: -0.1700
Data Index: 5386459 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8874. Min Act: -0.1700
Data Index: 3829270 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8561. Min Act: -0.1700
Data Index: 2750621 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8561. Min Act: -0.1700
Data Index: 6379905 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8561. Min Act: -0.1700
Data Index: 5839749 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8561. Min Act: -0.1700
Data Index: 1668444 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8561. Min Act: -0.1700
Data Index: 1910796 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.7936. Min Act: -0.1700
Data Index: 2417576 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.8249. Min Act: -0.1700
Data Index: 8563787 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.7936. Min Act: -0.1700
Data Index: 5421110 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.7936. Min Act: -0.1699
Data Index: 4338831 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3561. Min Range: -5.3561
Max Act: 4.7936. Min Act: -0.1700
Data Index: 1919415 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19