Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2443 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0774. Min Range: -3.0774
Max Act: 3.0774. Min Act: -0.1698
Data Index: 4347906 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0774. Min Range: -3.0774
Max Act: 3.0301. Min Act: -0.1700
Data Index: 6383505 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.9669. Min Act: -0.1700
Data Index: 1823539 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.9352. Min Act: -0.1700
Data Index: 5292971 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.9035. Min Act: -0.1700
Data Index: 4486529 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.9035. Min Act: -0.1700
Data Index: 5805740 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8718. Min Act: -0.1700
Data Index: 22841 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.9035. Min Act: -0.1700
Data Index: 5300803 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8400. Min Act: -0.1700
Data Index: 6655285 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8559. Min Act: -0.1700
Data Index: 327313 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8400. Min Act: -0.1700
Data Index: 6259161 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8559. Min Act: -0.1700
Data Index: 3401585 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8241. Min Act: -0.1700
Data Index: 3260353 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8082. Min Act: -0.1700
Data Index: 6925290 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8082. Min Act: -0.1700
Data Index: 5525961 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8241. Min Act: -0.1700
Data Index: 8535368 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8241. Min Act: -0.1700
Data Index: 7793507 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.8082. Min Act: -0.1700
Data Index: 1364129 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.7923. Min Act: -0.1700
Data Index: 559041 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0774. Min Range: -3.0774
Max Act: 2.7923. Min Act: -0.1700
Data Index: 5971261 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19