Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.5139. Min Act: -0.1700
Data Index: 5198238 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.2639. Min Act: -0.1700
Data Index: 7140214 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5139. Min Range: -6.5139
Max Act: 6.0451. Min Act: -0.1700
Data Index: 2352459 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4036343 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.8889. Min Act: -0.1700
Data Index: 4947090 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.8889. Min Act: -0.1700
Data Index: 229998 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.8889. Min Act: -0.1700
Data Index: 4948249 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.8264. Min Act: -0.1700
Data Index: 8626870 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.8264. Min Act: -0.1700
Data Index: 8785859 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7951. Min Act: -0.1700
Data Index: 3246644 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7951. Min Act: -0.1700
Data Index: 4600014 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 4645841 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 2051342 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7951. Min Act: -0.1700
Data Index: 4816765 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7951. Min Act: -0.1700
Data Index: 2296870 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 1634130 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 1246486 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7326. Min Act: -0.1700
Data Index: 2981038 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7014. Min Act: -0.1700
Data Index: 6835168 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5139. Min Range: -6.5139
Max Act: 5.7639. Min Act: -0.1700
Data Index: 7307659 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19