Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4783 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.5387. Min Act: -0.1700
Data Index: 6431090 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.5387. Min Act: -0.1700
Data Index: 251210 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.2574. Min Act: -0.1700
Data Index: 3235922 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.2262. Min Act: -0.1700
Data Index: 777613 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.2887. Min Act: -0.1700
Data Index: 8533231 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.2574. Min Act: -0.1700
Data Index: 8332545 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.1949. Min Act: -0.1700
Data Index: 5624674 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.1637. Min Act: -0.1700
Data Index: 8584796 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.1637. Min Act: -0.1700
Data Index: 1509111 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.1949. Min Act: -0.1700
Data Index: 1241064 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.1324. Min Act: -0.1700
Data Index: 7551471 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.1324. Min Act: -0.1700
Data Index: 7192031 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.1012. Min Act: -0.1700
Data Index: 5100294 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.0699. Min Act: -0.1700
Data Index: 4860714 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.0387. Min Act: -0.1700
Data Index: 1981737 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.0387. Min Act: -0.1700
Data Index: 8198395 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.0074. Min Act: -0.1700
Data Index: 179025 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.0387. Min Act: -0.1700
Data Index: 4835305 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5387. Min Range: -7.5387
Max Act: 7.0387. Min Act: -0.1700
Data Index: 4782415 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5387. Min Range: -7.5387
Max Act: 6.9762. Min Act: -0.1700
Data Index: 6282023 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19