Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5183 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.7868. Min Act: -0.1700
Data Index: 2487702 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.2556. Min Act: -0.1700
Data Index: 848494 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.1306. Min Act: -0.1700
Data Index: 6400849 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.1306. Min Act: -0.1700
Data Index: 4898938 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0993. Min Act: -0.1700
Data Index: 4568235 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.1306. Min Act: -0.1700
Data Index: 5532679 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0681. Min Act: -0.1700
Data Index: 7408826 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0681. Min Act: -0.1700
Data Index: 6320257 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0681. Min Act: -0.1700
Data Index: 7328333 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0368. Min Act: -0.1700
Data Index: 1562666 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0368. Min Act: -0.1700
Data Index: 8597639 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0368. Min Act: -0.1700
Data Index: 6254436 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0056. Min Act: -0.1700
Data Index: 7794631 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0368. Min Act: -0.1700
Data Index: 5796992 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0368. Min Act: -0.1700
Data Index: 3874586 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0368. Min Act: -0.1700
Data Index: 819383 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0368. Min Act: -0.1700
Data Index: 8719017 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0056. Min Act: -0.1700
Data Index: 3834632 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0056. Min Act: -0.1700
Data Index: 1871851 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7868. Min Range: -5.7868
Max Act: 5.0056. Min Act: -0.1700
Data Index: 553093 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19