Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5303 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3270. Min Range: -8.3270
Max Act: 8.3270. Min Act: -0.1700
Data Index: 8064713 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.8895. Min Act: -0.1700
Data Index: 1592302 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.6083. Min Act: -0.1700
Data Index: 4954136 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.6083. Min Act: -0.1700
Data Index: 865457 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.4833. Min Act: -0.1700
Data Index: 5982899 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.5145. Min Act: -0.1700
Data Index: 3682135 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.4833. Min Act: -0.1700
Data Index: 8745737 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.4520. Min Act: -0.1700
Data Index: 7992272 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.4520. Min Act: -0.1700
Data Index: 4679477 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.3895. Min Act: -0.1700
Data Index: 4163440 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.3895. Min Act: -0.1700
Data Index: 8355648 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.4208. Min Act: -0.1700
Data Index: 653902 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.3895. Min Act: -0.1700
Data Index: 8420822 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.3895. Min Act: -0.1700
Data Index: 949772 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.3583. Min Act: -0.1700
Data Index: 5771818 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.3270. Min Act: -0.1700
Data Index: 5216109 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.3270. Min Act: -0.1700
Data Index: 3816272 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.3270. Min Act: -0.1700
Data Index: 8496627 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.2645. Min Act: -0.1700
Data Index: 4637248 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3270. Min Range: -8.3270
Max Act: 7.3270. Min Act: -0.1700
Data Index: 5154787 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19