Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2486. Min Range: -7.2486
Max Act: 7.2486. Min Act: -0.1700
Data Index: 4311810 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2486. Min Range: -7.2486
Max Act: 7.1861. Min Act: -0.1700
Data Index: 7915758 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2486. Min Range: -7.2486
Max Act: 7.1861. Min Act: -0.1700
Data Index: 221842 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.9986. Min Act: -0.1700
Data Index: 6623909 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.9673. Min Act: -0.1700
Data Index: 36139 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.8111. Min Act: -0.1700
Data Index: 7377968 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.7798. Min Act: -0.1700
Data Index: 6732135 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.8111. Min Act: -0.1700
Data Index: 4398932 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.7798. Min Act: -0.1700
Data Index: 2359263 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.7798. Min Act: -0.1700
Data Index: 8784817 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.7486. Min Act: -0.1700
Data Index: 6869151 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.6861. Min Act: -0.1700
Data Index: 4366110 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.7173. Min Act: -0.1700
Data Index: 3988616 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.7173. Min Act: -0.1700
Data Index: 6544464 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.6861. Min Act: -0.1700
Data Index: 2136593 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.6861. Min Act: -0.1700
Data Index: 4139016 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.6861. Min Act: -0.1700
Data Index: 1529991 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.6236. Min Act: -0.1700
Data Index: 3902836 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.6548. Min Act: -0.1700
Data Index: 5021574 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2486. Min Range: -7.2486
Max Act: 6.6236. Min Act: -0.1700
Data Index: 6871386 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19