Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5272 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.6746. Min Range: -13.6746
Max Act: 13.6746. Min Act: -0.1700
Data Index: 8496697 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.6746. Min Range: -13.6746
Max Act: 13.1121. Min Act: -0.1700
Data Index: 1219904 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.8621. Min Act: -0.1700
Data Index: 1055911 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.7996. Min Act: -0.1700
Data Index: 2049913 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.7371. Min Act: -0.1700
Data Index: 8058040 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.7371. Min Act: -0.1700
Data Index: 4621255 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.6121. Min Act: -0.1700
Data Index: 5184765 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.6121. Min Act: -0.1700
Data Index: 5854026 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.2996. Min Act: -0.1700
Data Index: 4305965 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.2996. Min Act: -0.1700
Data Index: 1922013 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.3621. Min Act: -0.1700
Data Index: 5591316 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.3621. Min Act: -0.1700
Data Index: 3176403 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.2371. Min Act: -0.1699
Data Index: 7587541 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.1746. Min Act: -0.1700
Data Index: 621158 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.1746. Min Act: -0.1700
Data Index: 790935 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.1121. Min Act: -0.1700
Data Index: 7587542 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.0496. Min Act: -0.1700
Data Index: 8535658 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.6746. Min Range: -13.6746
Max Act: 12.0496. Min Act: -0.1700
Data Index: 7083955 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.6746. Min Range: -13.6746
Max Act: 11.9871. Min Act: -0.1700
Data Index: 7883067 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.6746. Min Range: -13.6746
Max Act: 11.9871. Min Act: -0.1700
Data Index: 8496168 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19