Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4780 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.9980. Min Act: -0.1700
Data Index: 2382173 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.8105. Min Act: -0.1700
Data Index: 3671016 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.7480. Min Act: -0.1700
Data Index: 552149 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.7167. Min Act: -0.1700
Data Index: 1370404 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.7167. Min Act: -0.1700
Data Index: 665916 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.6542. Min Act: -0.1700
Data Index: 6921778 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.6542. Min Act: -0.1700
Data Index: 734773 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.6542. Min Act: -0.1700
Data Index: 4477904 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.6542. Min Act: -0.1700
Data Index: 4909972 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.6230. Min Act: -0.1700
Data Index: 2977400 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.6230. Min Act: -0.1700
Data Index: 6260569 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.5917. Min Act: -0.1700
Data Index: 3025010 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.5917. Min Act: -0.1700
Data Index: 3553607 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.5917. Min Act: -0.1700
Data Index: 3545142 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.5917. Min Act: -0.1700
Data Index: 1805728 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.5917. Min Act: -0.1700
Data Index: 192141 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.5917. Min Act: -0.1700
Data Index: 6807233 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.5605. Min Act: -0.1700
Data Index: 902613 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.5605. Min Act: -0.1700
Data Index: 4879973 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9980. Min Range: -5.9980
Max Act: 5.5917. Min Act: -0.1700
Data Index: 2317285 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19