Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2756 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3196. Min Range: -8.3196
Max Act: 8.3196. Min Act: -0.1700
Data Index: 739920 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3196. Min Range: -8.3196
Max Act: 8.1946. Min Act: -0.1700
Data Index: 2248478 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3196. Min Range: -8.3196
Max Act: 8.1321. Min Act: -0.1700
Data Index: 6078762 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3196. Min Range: -8.3196
Max Act: 8.0384. Min Act: -0.1700
Data Index: 2058839 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3196. Min Range: -8.3196
Max Act: 8.0071. Min Act: -0.1700
Data Index: 246110 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.9759. Min Act: -0.1700
Data Index: 6562102 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3196. Min Range: -8.3196
Max Act: 8.0071. Min Act: -0.1700
Data Index: 2409108 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.9134. Min Act: -0.1700
Data Index: 7571730 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.9446. Min Act: -0.1700
Data Index: 522756 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.9134. Min Act: -0.1700
Data Index: 5771888 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.8821. Min Act: -0.1700
Data Index: 3946406 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.8821. Min Act: -0.1700
Data Index: 7183303 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.8821. Min Act: -0.1700
Data Index: 3365720 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.8509. Min Act: -0.1700
Data Index: 7871282 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.8509. Min Act: -0.1700
Data Index: 2284784 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.8196. Min Act: -0.1700
Data Index: 3449693 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.8196. Min Act: -0.1700
Data Index: 2355647 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.7571. Min Act: -0.1700
Data Index: 8645039 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.7259. Min Act: -0.1700
Data Index: 4778487 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3196. Min Range: -8.3196
Max Act: 7.7259. Min Act: -0.1700
Data Index: 2632124 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19