Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.5569. Min Act: -0.1700
Data Index: 6271026 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.5569. Min Act: -0.1700
Data Index: 1384169 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.3694. Min Act: -0.1700
Data Index: 3495649 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.3694. Min Act: -0.1700
Data Index: 5210366 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.3694. Min Act: -0.1700
Data Index: 6007041 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.3069. Min Act: -0.1700
Data Index: 4877049 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.3069. Min Act: -0.1700
Data Index: 3005724 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 5210362 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 1860048 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 6041632 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 4138029 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.1819. Min Act: -0.1700
Data Index: 4564801 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.2444. Min Act: -0.1700
Data Index: 4589556 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.1819. Min Act: -0.1700
Data Index: 8747160 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.1819. Min Act: -0.1700
Data Index: 8136444 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.1819. Min Act: -0.1700
Data Index: 7483415 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.1819. Min Act: -0.1700
Data Index: 7342155 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.1506. Min Act: -0.1700
Data Index: 1836718 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.1194. Min Act: -0.1700
Data Index: 1384173 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5569. Min Range: -8.5569
Max Act: 8.1194. Min Act: -0.1700
Data Index: 3319133 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19