Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5532 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.8933. Min Act: -0.1700
Data Index: 94318 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.6746. Min Act: -0.1700
Data Index: 8161413 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.5496. Min Act: -0.1700
Data Index: 5238398 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.5496. Min Act: -0.1700
Data Index: 7361685 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.5183. Min Act: -0.1700
Data Index: 5241503 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.4871. Min Act: -0.1700
Data Index: 8295328 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.4871. Min Act: -0.1700
Data Index: 8112870 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.4558. Min Act: -0.1700
Data Index: 8112886 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.4246. Min Act: -0.1700
Data Index: 4508639 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3933. Min Act: -0.1700
Data Index: 5462236 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3933. Min Act: -0.1700
Data Index: 8295338 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3933. Min Act: -0.1700
Data Index: 2701364 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3621. Min Act: -0.1700
Data Index: 2556858 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3621. Min Act: -0.1700
Data Index: 3143809 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3308. Min Act: -0.1700
Data Index: 4852773 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3621. Min Act: -0.1700
Data Index: 7342023 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3308. Min Act: -0.1700
Data Index: 4993846 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3308. Min Act: -0.1700
Data Index: 1780921 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3308. Min Act: -0.1700
Data Index: 6090573 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8933. Min Range: -5.8933
Max Act: 5.3308. Min Act: -0.1700
Data Index: 6827849 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19