Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3010 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1087. Min Range: -5.1087
Max Act: 5.1087. Min Act: -0.1700
Data Index: 379420 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1087. Min Range: -5.1087
Max Act: 5.0774. Min Act: -0.1700
Data Index: 4932960 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1087. Min Range: -5.1087
Max Act: 5.0774. Min Act: -0.1700
Data Index: 174993 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9837. Min Act: -0.1700
Data Index: 1785113 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1087. Min Range: -5.1087
Max Act: 5.0462. Min Act: -0.1700
Data Index: 7661549 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9524. Min Act: -0.1700
Data Index: 7054955 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9837. Min Act: -0.1700
Data Index: 2222463 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9524. Min Act: -0.1700
Data Index: 7262017 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.8899. Min Act: -0.1700
Data Index: 426339 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9212. Min Act: -0.1700
Data Index: 4335849 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9212. Min Act: -0.1700
Data Index: 3676032 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9212. Min Act: -0.1700
Data Index: 8415101 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9524. Min Act: -0.1700
Data Index: 3509667 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9212. Min Act: -0.1700
Data Index: 3431135 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.8899. Min Act: -0.1700
Data Index: 3854657 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.9212. Min Act: -0.1700
Data Index: 4138851 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.8899. Min Act: -0.1700
Data Index: 3387101 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.8899. Min Act: -0.1700
Data Index: 1984929 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.8587. Min Act: -0.1700
Data Index: 483710 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1087. Min Range: -5.1087
Max Act: 4.8274. Min Act: -0.1700
Data Index: 6799074 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19