Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4294 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.9375. Min Act: -0.1700
Data Index: 6307979 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.9063. Min Act: -0.1700
Data Index: 4085527 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.9063. Min Act: -0.1700
Data Index: 4757674 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.9063. Min Act: -0.1700
Data Index: 23259 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.9063. Min Act: -0.1700
Data Index: 6898758 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8750. Min Act: -0.1700
Data Index: 4104311 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8750. Min Act: -0.1700
Data Index: 2948754 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8750. Min Act: -0.1700
Data Index: 8631998 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8750. Min Act: -0.1700
Data Index: 76437 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8437. Min Act: -0.1700
Data Index: 7294877 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8125. Min Act: -0.1700
Data Index: 8269924 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8125. Min Act: -0.1700
Data Index: 6452753 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8125. Min Act: -0.1700
Data Index: 8649957 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8125. Min Act: -0.1700
Data Index: 2352987 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8125. Min Act: -0.1700
Data Index: 4128233 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7812. Min Act: -0.1700
Data Index: 1764219 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7812. Min Act: -0.1700
Data Index: 6260778 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7499. Min Act: -0.1700
Data Index: 1836803 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7812. Min Act: -0.1700
Data Index: 40068 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7499. Min Act: -0.1700
Data Index: 4884492 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19