Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4861 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.7996. Min Act: -0.1700
Data Index: 4990860 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.6746. Min Act: -0.1700
Data Index: 1763248 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.6746. Min Act: -0.1700
Data Index: 2532443 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.6746. Min Act: -0.1700
Data Index: 8163264 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.6121. Min Act: -0.1700
Data Index: 6071530 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.6121. Min Act: -0.1700
Data Index: 8687949 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.5496. Min Act: -0.1700
Data Index: 2817697 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.5496. Min Act: -0.1700
Data Index: 1683316 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.4871. Min Act: -0.1700
Data Index: 2961694 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.3621. Min Act: -0.1700
Data Index: 1858472 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.3621. Min Act: -0.1700
Data Index: 816461 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.3621. Min Act: -0.1700
Data Index: 7463519 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.3621. Min Act: -0.1700
Data Index: 1006883 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.2996. Min Act: -0.1700
Data Index: 4423919 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.2996. Min Act: -0.1700
Data Index: 5727880 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.2996. Min Act: -0.1700
Data Index: 3713753 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.2996. Min Act: -0.1700
Data Index: 7292446 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.2996. Min Act: -0.1700
Data Index: 4545418 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.2996. Min Act: -0.1700
Data Index: 3181108 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7996. Min Range: -8.7996
Max Act: 8.2371. Min Act: -0.1700
Data Index: 5709522 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19