Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7437. Min Range: -7.7437
Max Act: 7.7437. Min Act: -0.1700
Data Index: 4037432 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.9000. Min Act: -0.1700
Data Index: 1891175 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.7750. Min Act: -0.1700
Data Index: 2552477 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.7437. Min Act: -0.1700
Data Index: 6934214 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.6812. Min Act: -0.1700
Data Index: 8386705 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.6500. Min Act: -0.1700
Data Index: 7920563 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.6187. Min Act: -0.1700
Data Index: 5402594 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.6187. Min Act: -0.1700
Data Index: 1554682 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.6187. Min Act: -0.1700
Data Index: 4154450 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.5562. Min Act: -0.1700
Data Index: 5157041 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.5562. Min Act: -0.1700
Data Index: 2552473 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.5562. Min Act: -0.1700
Data Index: 5228046 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.5562. Min Act: -0.1700
Data Index: 3353262 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.4937. Min Act: -0.1700
Data Index: 2725019 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.4625. Min Act: -0.1700
Data Index: 967506 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.4937. Min Act: -0.1700
Data Index: 7962814 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.4625. Min Act: -0.1700
Data Index: 4595936 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.4625. Min Act: -0.1700
Data Index: 2552476 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.4312. Min Act: -0.1700
Data Index: 490743 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7437. Min Range: -7.7437
Max Act: 6.4312. Min Act: -0.1700
Data Index: 4595212 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19