Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1415 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2732. Min Range: -6.2732
Max Act: 6.2732. Min Act: -0.1700
Data Index: 4605955 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2732. Min Range: -6.2732
Max Act: 6.0857. Min Act: -0.1700
Data Index: 8282635 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2732. Min Range: -6.2732
Max Act: 6.0232. Min Act: -0.1700
Data Index: 8443941 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.9919. Min Act: -0.1700
Data Index: 6140375 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.9607. Min Act: -0.1700
Data Index: 3744813 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.9607. Min Act: -0.1700
Data Index: 2598222 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.9607. Min Act: -0.1700
Data Index: 679184 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.9294. Min Act: -0.1700
Data Index: 3113439 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.9294. Min Act: -0.1700
Data Index: 3134444 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8982. Min Act: -0.1700
Data Index: 3578596 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8669. Min Act: -0.1700
Data Index: 6446034 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8982. Min Act: -0.1700
Data Index: 6961146 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8982. Min Act: -0.1700
Data Index: 6598530 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8982. Min Act: -0.1700
Data Index: 3895717 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8982. Min Act: -0.1700
Data Index: 7512774 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8669. Min Act: -0.1700
Data Index: 2429074 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8669. Min Act: -0.1700
Data Index: 4742911 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8669. Min Act: -0.1700
Data Index: 1139792 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8357. Min Act: -0.1700
Data Index: 7879109 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2732. Min Range: -6.2732
Max Act: 5.8357. Min Act: -0.1700
Data Index: 4185821 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19