Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.9573. Min Act: -0.1700
Data Index: 4806241 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.9417. Min Act: -0.1700
Data Index: 1212561 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.8948. Min Act: -0.1700
Data Index: 8820634 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.8948. Min Act: -0.1700
Data Index: 1706026 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.8791. Min Act: -0.1700
Data Index: 7962790 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.8479. Min Act: -0.1700
Data Index: 5870912 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.8635. Min Act: -0.1700
Data Index: 724861 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.8479. Min Act: -0.1700
Data Index: 2318231 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.8166. Min Act: -0.1700
Data Index: 1544195 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.8010. Min Act: -0.1700
Data Index: 795670 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.8010. Min Act: -0.1700
Data Index: 2897012 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.7697. Min Act: -0.1700
Data Index: 2016096 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.7853. Min Act: -0.1700
Data Index: 2933051 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.7853. Min Act: -0.1700
Data Index: 762804 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.7853. Min Act: -0.1700
Data Index: 201423 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.7853. Min Act: -0.1700
Data Index: 6120915 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.7853. Min Act: -0.1700
Data Index: 2100377 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.7853. Min Act: -0.1700
Data Index: 6649025 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.7697. Min Act: -0.1700
Data Index: 3871895 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9573. Min Range: -3.9573
Max Act: 3.7540. Min Act: -0.1700
Data Index: 3582479 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19