Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 807 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6063. Min Range: -8.6063
Max Act: 8.6063. Min Act: -0.1700
Data Index: 5864286 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6063. Min Range: -8.6063
Max Act: 8.5438. Min Act: -0.1700
Data Index: 3620789 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6063. Min Range: -8.6063
Max Act: 8.4813. Min Act: -0.1700
Data Index: 485677 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6063. Min Range: -8.6063
Max Act: 8.4188. Min Act: -0.1700
Data Index: 7105941 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6063. Min Range: -8.6063
Max Act: 8.2313. Min Act: -0.1700
Data Index: 7686755 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6063. Min Range: -8.6063
Max Act: 8.2938. Min Act: -0.1700
Data Index: 2944770 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6063. Min Range: -8.6063
Max Act: 8.1063. Min Act: -0.1700
Data Index: 5071464 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6063. Min Range: -8.6063
Max Act: 8.0438. Min Act: -0.1700
Data Index: 7352117 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.9813. Min Act: -0.1700
Data Index: 1646921 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.9813. Min Act: -0.1700
Data Index: 2749710 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.9188. Min Act: -0.1700
Data Index: 591180 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.9188. Min Act: -0.1700
Data Index: 3221469 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.8563. Min Act: -0.1700
Data Index: 5461347 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.7313. Min Act: -0.1700
Data Index: 4337182 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.7313. Min Act: -0.1700
Data Index: 6357889 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.7313. Min Act: -0.1700
Data Index: 4882312 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.7313. Min Act: -0.1700
Data Index: 5082430 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.6688. Min Act: -0.1700
Data Index: 1525320 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.6688. Min Act: -0.1700
Data Index: 3647354 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6063. Min Range: -8.6063
Max Act: 7.6063. Min Act: -0.1700
Data Index: 2302217 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19