Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1004. Min Range: -9.1004
Max Act: 9.1004. Min Act: -0.1700
Data Index: 3212541 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1004. Min Range: -9.1004
Max Act: 9.1004. Min Act: -0.1700
Data Index: 6777677 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1004. Min Range: -9.1004
Max Act: 9.0379. Min Act: -0.1700
Data Index: 2400275 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.8504. Min Act: -0.1700
Data Index: 2930556 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.7254. Min Act: -0.1700
Data Index: 6033082 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.7254. Min Act: -0.1700
Data Index: 95508 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.7254. Min Act: -0.1700
Data Index: 6914294 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.7254. Min Act: -0.1700
Data Index: 7105017 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.6629. Min Act: -0.1700
Data Index: 8333041 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.6629. Min Act: -0.1700
Data Index: 6496044 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.6629. Min Act: -0.1700
Data Index: 4451740 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.6004. Min Act: -0.1700
Data Index: 1072199 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.6629. Min Act: -0.1700
Data Index: 5950139 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.6004. Min Act: -0.1700
Data Index: 2291265 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.6004. Min Act: -0.1700
Data Index: 3946932 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.6004. Min Act: -0.1700
Data Index: 1109100 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.6004. Min Act: -0.1700
Data Index: 528583 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.5379. Min Act: -0.1700
Data Index: 3965209 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.5379. Min Act: -0.1700
Data Index: 7188619 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1004. Min Range: -9.1004
Max Act: 8.5379. Min Act: -0.1700
Data Index: 3616213 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19