Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3167. Min Range: -9.3167
Max Act: 9.3167. Min Act: -0.1700
Data Index: 6121559 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.8792. Min Act: -0.1700
Data Index: 3844168 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.8167. Min Act: -0.1700
Data Index: 5672050 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.8167. Min Act: -0.1700
Data Index: 6371444 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.5667. Min Act: -0.1700
Data Index: 2473598 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.5667. Min Act: -0.1700
Data Index: 7196377 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.5667. Min Act: -0.1700
Data Index: 243823 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.5667. Min Act: -0.1700
Data Index: 3120999 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.5042. Min Act: -0.1700
Data Index: 5888414 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.5042. Min Act: -0.1700
Data Index: 2610296 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.5042. Min Act: -0.1700
Data Index: 5260837 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.5042. Min Act: -0.1700
Data Index: 1262985 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.4417. Min Act: -0.1700
Data Index: 1579939 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.4417. Min Act: -0.1700
Data Index: 2762479 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.3792. Min Act: -0.1700
Data Index: 8305295 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.3792. Min Act: -0.1700
Data Index: 3512196 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.3167. Min Act: -0.1700
Data Index: 8045555 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.3167. Min Act: -0.1700
Data Index: 7663245 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.3167. Min Act: -0.1700
Data Index: 6471626 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3167. Min Range: -9.3167
Max Act: 8.2542. Min Act: -0.1700
Data Index: 482989 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19