Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2732 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1313. Min Range: -5.1313
Max Act: 5.1313. Min Act: -0.1700
Data Index: 8800318 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1313. Min Range: -5.1313
Max Act: 5.1001. Min Act: -0.1700
Data Index: 7373159 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1313. Min Range: -5.1313
Max Act: 5.0688. Min Act: -0.1700
Data Index: 2465683 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1313. Min Range: -5.1313
Max Act: 5.0376. Min Act: -0.1700
Data Index: 6436366 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9751. Min Act: -0.1700
Data Index: 2858612 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9751. Min Act: -0.1700
Data Index: 5129188 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9438. Min Act: -0.1700
Data Index: 5053671 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9751. Min Act: -0.1700
Data Index: 7613512 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9438. Min Act: -0.1700
Data Index: 2049661 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.8813. Min Act: -0.1700
Data Index: 3113698 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9126. Min Act: -0.1700
Data Index: 8041326 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9126. Min Act: -0.1700
Data Index: 2318934 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9126. Min Act: -0.1700
Data Index: 1697441 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9126. Min Act: -0.1700
Data Index: 5607460 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.8813. Min Act: -0.1700
Data Index: 6591435 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.8501. Min Act: -0.1700
Data Index: 7971219 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.9126. Min Act: -0.1700
Data Index: 633633 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.8501. Min Act: -0.1700
Data Index: 4173459 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.8501. Min Act: -0.1700
Data Index: 4313678 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1313. Min Range: -5.1313
Max Act: 4.8501. Min Act: -0.1700
Data Index: 1749657 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19