Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2626 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.7648. Min Act: -0.1700
Data Index: 6857013 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.7648. Min Act: -0.1700
Data Index: 1245851 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.7023. Min Act: -0.1700
Data Index: 5816320 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.7023. Min Act: -0.1700
Data Index: 7555231 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.7023. Min Act: -0.1700
Data Index: 6780120 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.7023. Min Act: -0.1700
Data Index: 6228084 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.7648. Min Act: -0.1700
Data Index: 5838932 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 3144115 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 6107823 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 1369502 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 2488402 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 5151653 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 7914062 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 1955389 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 8288574 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 4483857 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 4508025 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 8519002 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 615276 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7648. Min Range: -7.7648
Max Act: 7.6398. Min Act: -0.1700
Data Index: 615275 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19