Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5391 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1076. Min Range: -7.1076
Max Act: 7.1076. Min Act: -0.1700
Data Index: 6196372 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.6701. Min Act: -0.1700
Data Index: 3312805 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.5764. Min Act: -0.1700
Data Index: 7110261 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.3576. Min Act: -0.1700
Data Index: 7735502 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.2951. Min Act: -0.1700
Data Index: 6784563 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.2639. Min Act: -0.1700
Data Index: 6028806 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.2326. Min Act: -0.1700
Data Index: 1737597 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.2326. Min Act: -0.1700
Data Index: 7924586 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.1701. Min Act: -0.1700
Data Index: 2646805 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.1701. Min Act: -0.1700
Data Index: 3349902 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.1389. Min Act: -0.1700
Data Index: 3919780 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1076. Min Range: -7.1076
Max Act: 6.0139. Min Act: -0.1700
Data Index: 2408693 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1076. Min Range: -7.1076
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4937777 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1076. Min Range: -7.1076
Max Act: 5.9201. Min Act: -0.1700
Data Index: 6773416 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1076. Min Range: -7.1076
Max Act: 5.9201. Min Act: -0.1700
Data Index: 1839442 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1076. Min Range: -7.1076
Max Act: 5.9201. Min Act: -0.1700
Data Index: 7964131 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1076. Min Range: -7.1076
Max Act: 5.8889. Min Act: -0.1700
Data Index: 3656470 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1076. Min Range: -7.1076
Max Act: 5.8889. Min Act: -0.1700
Data Index: 5620174 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1076. Min Range: -7.1076
Max Act: 5.8576. Min Act: -0.1700
Data Index: 3467456 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1076. Min Range: -7.1076
Max Act: 5.8576. Min Act: -0.1700
Data Index: 1034639 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19