Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4051 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.7848. Min Act: -0.1700
Data Index: 6830734 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.4098. Min Act: -0.1700
Data Index: 1428513 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.2223. Min Act: -0.1700
Data Index: 999168 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.1911. Min Act: -0.1700
Data Index: 1813852 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.1911. Min Act: -0.1700
Data Index: 5205366 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.0661. Min Act: -0.1700
Data Index: 7733666 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.0661. Min Act: -0.1700
Data Index: 8050889 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.0661. Min Act: -0.1700
Data Index: 5190786 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.0661. Min Act: -0.1700
Data Index: 5365180 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7848. Min Range: -6.7848
Max Act: 6.0036. Min Act: -0.1700
Data Index: 7565934 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.9723. Min Act: -0.1700
Data Index: 5367315 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.9723. Min Act: -0.1700
Data Index: 5659329 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.9411. Min Act: -0.1700
Data Index: 1000164 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.9098. Min Act: -0.1700
Data Index: 5726342 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.9098. Min Act: -0.1700
Data Index: 3766289 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.9098. Min Act: -0.1700
Data Index: 8625098 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.9098. Min Act: -0.1700
Data Index: 1541091 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.8786. Min Act: -0.1700
Data Index: 4434795 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.8473. Min Act: -0.1700
Data Index: 4483599 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7848. Min Range: -6.7848
Max Act: 5.8473. Min Act: -0.1700
Data Index: 5938158 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19