Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1342 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.7643. Min Act: -0.1700
Data Index: 2783863 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.6705. Min Act: -0.1700
Data Index: 6255132 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.6080. Min Act: -0.1700
Data Index: 5458932 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.6080. Min Act: -0.1700
Data Index: 5458934 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.5768. Min Act: -0.1700
Data Index: 1462914 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.6080. Min Act: -0.1700
Data Index: 5458927 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.6393. Min Act: -0.1700
Data Index: 7267490 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.6080. Min Act: -0.1700
Data Index: 5827821 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.5768. Min Act: -0.1700
Data Index: 4266757 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.5143. Min Act: -0.1700
Data Index: 2584701 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.4830. Min Act: -0.1700
Data Index: 5403064 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.4830. Min Act: -0.1700
Data Index: 6081461 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.5143. Min Act: -0.1700
Data Index: 3784887 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.4518. Min Act: -0.1700
Data Index: 4494814 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.4518. Min Act: -0.1700
Data Index: 1938225 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.4205. Min Act: -0.1700
Data Index: 7158831 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.4205. Min Act: -0.1700
Data Index: 694027 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.4205. Min Act: -0.1700
Data Index: 7158888 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.4205. Min Act: -0.1700
Data Index: 7932421 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7643. Min Range: -5.7643
Max Act: 5.4205. Min Act: -0.1700
Data Index: 7098298 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19