Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5778 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.6484. Min Act: -0.1700
Data Index: 6114228 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.6484. Min Act: -0.1700
Data Index: 6969000 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.5547. Min Act: -0.1700
Data Index: 7852112 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.5234. Min Act: -0.1700
Data Index: 3723133 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.4609. Min Act: -0.1700
Data Index: 2990998 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.3672. Min Act: -0.1700
Data Index: 8679250 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.3359. Min Act: -0.1700
Data Index: 1415505 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.2734. Min Act: -0.1700
Data Index: 316357 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.2422. Min Act: -0.1700
Data Index: 1854516 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.2109. Min Act: -0.1700
Data Index: 3881890 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.2109. Min Act: -0.1700
Data Index: 8665524 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.1797. Min Act: -0.1700
Data Index: 729946 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.2109. Min Act: -0.1700
Data Index: 8034587 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.1484. Min Act: -0.1700
Data Index: 6197436 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.1172. Min Act: -0.1700
Data Index: 4539979 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.1172. Min Act: -0.1700
Data Index: 5883108 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.1172. Min Act: -0.1700
Data Index: 332716 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.1172. Min Act: -0.1700
Data Index: 262613 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.0859. Min Act: -0.1700
Data Index: 4029890 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6484. Min Range: -6.6484
Max Act: 6.0859. Min Act: -0.1700
Data Index: 6564631 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19