Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4541 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.3976. Min Act: -0.1700
Data Index: 8626205 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.2414. Min Act: -0.1700
Data Index: 1250563 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.1789. Min Act: -0.1700
Data Index: 6241753 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.1789. Min Act: -0.1700
Data Index: 1889097 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.1476. Min Act: -0.1700
Data Index: 4000912 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.1476. Min Act: -0.1700
Data Index: 3625203 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.0851. Min Act: -0.1700
Data Index: 8113398 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.0851. Min Act: -0.1700
Data Index: 7757004 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.0851. Min Act: -0.1700
Data Index: 7773891 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.0539. Min Act: -0.1700
Data Index: 8785767 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.0539. Min Act: -0.1700
Data Index: 1469304 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.0851. Min Act: -0.1700
Data Index: 8111707 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.0226. Min Act: -0.1700
Data Index: 793890 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3976. Min Range: -5.3976
Max Act: 5.0226. Min Act: -0.1700
Data Index: 11578 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3976. Min Range: -5.3976
Max Act: 4.9601. Min Act: -0.1700
Data Index: 5252378 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3976. Min Range: -5.3976
Max Act: 4.9914. Min Act: -0.1700
Data Index: 3420005 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3976. Min Range: -5.3976
Max Act: 4.9601. Min Act: -0.1700
Data Index: 4690761 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3976. Min Range: -5.3976
Max Act: 4.9289. Min Act: -0.1700
Data Index: 3858149 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3976. Min Range: -5.3976
Max Act: 4.8976. Min Act: -0.1700
Data Index: 1835210 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3976. Min Range: -5.3976
Max Act: 4.9289. Min Act: -0.1700
Data Index: 4250278 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19