Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.7660. Min Act: -0.1700
Data Index: 5719191 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.7347. Min Act: -0.1700
Data Index: 2379432 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.7660. Min Act: -0.1700
Data Index: 1783234 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.7347. Min Act: -0.1700
Data Index: 7286156 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.7035. Min Act: -0.1700
Data Index: 3936723 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.7035. Min Act: -0.1700
Data Index: 7917396 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.7347. Min Act: -0.1700
Data Index: 1288488 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.6722. Min Act: -0.1700
Data Index: 4515400 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.6410. Min Act: -0.1700
Data Index: 1039123 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.6410. Min Act: -0.1700
Data Index: 27902 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.6097. Min Act: -0.1700
Data Index: 2084008 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.6097. Min Act: -0.1700
Data Index: 3036467 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.5785. Min Act: -0.1700
Data Index: 1436624 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.5785. Min Act: -0.1699
Data Index: 1005988 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.5785. Min Act: -0.1700
Data Index: 2891472 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.5785. Min Act: -0.1700
Data Index: 8751075 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.5160. Min Act: -0.1700
Data Index: 5619121 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.5472. Min Act: -0.1700
Data Index: 2894470 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.5472. Min Act: -0.1700
Data Index: 3731794 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7660. Min Range: -5.7660
Max Act: 5.5472. Min Act: -0.1700
Data Index: 4762778 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19