Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1870 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4760. Min Range: -6.4760
Max Act: 6.4760. Min Act: -0.1700
Data Index: 726245 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4760. Min Range: -6.4760
Max Act: 6.3510. Min Act: -0.1700
Data Index: 1038789 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4760. Min Range: -6.4760
Max Act: 6.2885. Min Act: -0.1700
Data Index: 693435 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4760. Min Range: -6.4760
Max Act: 6.1010. Min Act: -0.1700
Data Index: 6186397 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4760. Min Range: -6.4760
Max Act: 6.1010. Min Act: -0.1700
Data Index: 5381530 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4760. Min Range: -6.4760
Max Act: 6.0385. Min Act: -0.1700
Data Index: 3797242 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4760. Min Range: -6.4760
Max Act: 6.0073. Min Act: -0.1700
Data Index: 283292 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4760. Min Range: -6.4760
Max Act: 6.0073. Min Act: -0.1700
Data Index: 5785297 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.9760. Min Act: -0.1700
Data Index: 5610051 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.9760. Min Act: -0.1700
Data Index: 8439537 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.9760. Min Act: -0.1700
Data Index: 819655 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.9760. Min Act: -0.1700
Data Index: 2925810 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.9760. Min Act: -0.1700
Data Index: 8359749 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.9448. Min Act: -0.1700
Data Index: 6951971 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.9135. Min Act: -0.1700
Data Index: 5291730 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.9135. Min Act: -0.1700
Data Index: 1524245 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.9135. Min Act: -0.1700
Data Index: 6252273 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.8823. Min Act: -0.1700
Data Index: 1410599 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.8823. Min Act: -0.1700
Data Index: 6932617 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4760. Min Range: -6.4760
Max Act: 5.8823. Min Act: -0.1700
Data Index: 4094220 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19