Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4982 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.7563. Min Act: -0.1700
Data Index: 5567508 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6938. Min Act: -0.1700
Data Index: 947142 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.7251. Min Act: -0.1700
Data Index: 4533988 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6938. Min Act: -0.1700
Data Index: 1824412 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6938. Min Act: -0.1700
Data Index: 7210596 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6938. Min Act: -0.1700
Data Index: 2661969 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6313. Min Act: -0.1700
Data Index: 6043175 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6626. Min Act: -0.1700
Data Index: 7071401 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6313. Min Act: -0.1700
Data Index: 1399235 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6001. Min Act: -0.1700
Data Index: 3049994 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.6001. Min Act: -0.1700
Data Index: 4063676 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5688. Min Act: -0.1700
Data Index: 4402592 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5688. Min Act: -0.1700
Data Index: 748423 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5688. Min Act: -0.1700
Data Index: 4673452 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5688. Min Act: -0.1700
Data Index: 7846822 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5376. Min Act: -0.1700
Data Index: 6427834 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5376. Min Act: -0.1700
Data Index: 4567328 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5376. Min Act: -0.1700
Data Index: 4784491 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5376. Min Act: -0.1700
Data Index: 3278981 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7563. Min Range: -5.7563
Max Act: 5.5376. Min Act: -0.1700
Data Index: 3991860 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19