Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.7519. Min Act: -0.1700
Data Index: 103890 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.7206. Min Act: -0.1700
Data Index: 3314966 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.6581. Min Act: -0.1700
Data Index: 3314965 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.5644. Min Act: -0.1700
Data Index: 959662 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.5956. Min Act: -0.1700
Data Index: 4150687 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.5331. Min Act: -0.1700
Data Index: 6535488 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.5644. Min Act: -0.1700
Data Index: 3314964 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.5018. Min Act: -0.1700
Data Index: 5900053 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.5018. Min Act: -0.1700
Data Index: 7746452 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.5018. Min Act: -0.1700
Data Index: 8583148 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.4706. Min Act: -0.1700
Data Index: 5900052 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.4706. Min Act: -0.1700
Data Index: 6431492 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.4081. Min Act: -0.1700
Data Index: 7522864 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.4393. Min Act: -0.1700
Data Index: 5289271 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.4393. Min Act: -0.1700
Data Index: 6872841 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.4081. Min Act: -0.1700
Data Index: 3051379 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.4393. Min Act: -0.1700
Data Index: 5285335 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.4081. Min Act: -0.1700
Data Index: 7236591 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.3456. Min Act: -0.1700
Data Index: 4030766 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7519. Min Range: -4.7519
Max Act: 4.3768. Min Act: -0.1700
Data Index: 2415552 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19