Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6027 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2229. Min Range: -7.2229
Max Act: 7.2229. Min Act: -0.1700
Data Index: 4355175 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.9729. Min Act: -0.1700
Data Index: 7760435 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.9104. Min Act: -0.1700
Data Index: 1666130 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.9417. Min Act: -0.1700
Data Index: 954975 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.8479. Min Act: -0.1700
Data Index: 4218282 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.8167. Min Act: -0.1700
Data Index: 5020467 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.8167. Min Act: -0.1700
Data Index: 4204744 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.7854. Min Act: -0.1700
Data Index: 3170383 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.7854. Min Act: -0.1700
Data Index: 4218284 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.7542. Min Act: -0.1700
Data Index: 6876920 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.7542. Min Act: -0.1700
Data Index: 3033378 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.7542. Min Act: -0.1700
Data Index: 2348633 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.7542. Min Act: -0.1700
Data Index: 6981678 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.7229. Min Act: -0.1700
Data Index: 8524939 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.7229. Min Act: -0.1700
Data Index: 5417966 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.6917. Min Act: -0.1700
Data Index: 1434694 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.6917. Min Act: -0.1700
Data Index: 456526 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.7229. Min Act: -0.1700
Data Index: 7099506 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.6917. Min Act: -0.1700
Data Index: 4218283 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2229. Min Range: -7.2229
Max Act: 6.6604. Min Act: -0.1700
Data Index: 5777512 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19