Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.5721. Min Act: -0.1700
Data Index: 3880695 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.5721. Min Act: -0.1700
Data Index: 7260307 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.5096. Min Act: -0.1700
Data Index: 3922415 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.4471. Min Act: -0.1700
Data Index: 2146434 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.3221. Min Act: -0.1700
Data Index: 5617953 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.2596. Min Act: -0.1700
Data Index: 3431084 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.1971. Min Act: -0.1700
Data Index: 1780229 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.1971. Min Act: -0.1700
Data Index: 1078523 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.2596. Min Act: -0.1700
Data Index: 388351 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.1971. Min Act: -0.1700
Data Index: 4991085 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.1346. Min Act: -0.1700
Data Index: 2557513 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.1346. Min Act: -0.1700
Data Index: 7416303 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.1346. Min Act: -0.1700
Data Index: 6476644 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.1346. Min Act: -0.1700
Data Index: 6914246 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.0721. Min Act: -0.1700
Data Index: 5149797 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.0721. Min Act: -0.1700
Data Index: 1913963 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.0721. Min Act: -0.1700
Data Index: 6038445 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.0721. Min Act: -0.1700
Data Index: 3811294 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.0721. Min Act: -0.1700
Data Index: 6500760 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5721. Min Range: -8.5721
Max Act: 8.0721. Min Act: -0.1700
Data Index: 69645 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19