Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3808 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.6910. Min Act: -0.1700
Data Index: 6983428 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.3785. Min Act: -0.1700
Data Index: 6211845 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.3785. Min Act: -0.1700
Data Index: 8784763 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.3160. Min Act: -0.1700
Data Index: 6596087 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.3160. Min Act: -0.1700
Data Index: 2333526 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.3160. Min Act: -0.1700
Data Index: 4327600 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.2535. Min Act: -0.1700
Data Index: 6873641 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.2535. Min Act: -0.1700
Data Index: 3134061 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.2535. Min Act: -0.1700
Data Index: 7548696 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.1910. Min Act: -0.1700
Data Index: 1113926 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.1910. Min Act: -0.1700
Data Index: 5508676 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.1910. Min Act: -0.1700
Data Index: 3582489 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.1285. Min Act: -0.1700
Data Index: 5559477 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.1285. Min Act: -0.1700
Data Index: 4213127 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.0660. Min Act: -0.1700
Data Index: 5894102 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.1285. Min Act: -0.1700
Data Index: 8420347 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.0660. Min Act: -0.1700
Data Index: 2364594 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.0035. Min Act: -0.1700
Data Index: 1634057 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.0035. Min Act: -0.1700
Data Index: 5976605 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6910. Min Range: -8.6910
Max Act: 8.0035. Min Act: -0.1700
Data Index: 3158296 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19