Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.9428. Min Act: -0.1700
Data Index: 3184935 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.1928. Min Act: -0.1700
Data Index: 5879692 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.1303. Min Act: -0.1700
Data Index: 2272288 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.1303. Min Act: -0.1700
Data Index: 960063 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.1303. Min Act: -0.1700
Data Index: 4591033 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.0990. Min Act: -0.1700
Data Index: 729924 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.0990. Min Act: -0.1700
Data Index: 7029548 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.0990. Min Act: -0.1700
Data Index: 2895863 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.0678. Min Act: -0.1700
Data Index: 7836078 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.0365. Min Act: -0.1700
Data Index: 5199128 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.0365. Min Act: -0.1700
Data Index: 3557645 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.0053. Min Act: -0.1700
Data Index: 4435157 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.0053. Min Act: -0.1700
Data Index: 575813 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9428. Min Range: -6.9428
Max Act: 6.0053. Min Act: -0.1700
Data Index: 1936424 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9428. Min Range: -6.9428
Max Act: 5.9740. Min Act: -0.1700
Data Index: 7807040 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9428. Min Range: -6.9428
Max Act: 5.9428. Min Act: -0.1700
Data Index: 6357973 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9428. Min Range: -6.9428
Max Act: 5.9115. Min Act: -0.1700
Data Index: 5577891 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9428. Min Range: -6.9428
Max Act: 5.9115. Min Act: -0.1700
Data Index: 4442333 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9428. Min Range: -6.9428
Max Act: 5.9115. Min Act: -0.1700
Data Index: 2450439 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9428. Min Range: -6.9428
Max Act: 5.9428. Min Act: -0.1700
Data Index: 3598921 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19