Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.9550. Min Act: -0.1700
Data Index: 588052 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.9550. Min Act: -0.1700
Data Index: 3350213 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.9550. Min Act: -0.1700
Data Index: 2408447 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.8925. Min Act: -0.1700
Data Index: 6255332 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.8300. Min Act: -0.1700
Data Index: 418782 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.8300. Min Act: -0.1700
Data Index: 1774003 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7675. Min Act: -0.1700
Data Index: 2255351 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 5168054 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 742980 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 2534534 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 4770241 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 541340 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 8205134 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 3821144 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 6537683 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.6425. Min Act: -0.1700
Data Index: 5577320 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 5422475 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.6425. Min Act: -0.1700
Data Index: 2623612 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.7050. Min Act: -0.1700
Data Index: 4842129 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9550. Min Range: -7.9550
Max Act: 7.6425. Min Act: -0.1700
Data Index: 2895476 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19