Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.3935. Min Act: -0.1700
Data Index: 5528888 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.3623. Min Act: -0.1700
Data Index: 7939483 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.3623. Min Act: -0.1700
Data Index: 656349 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.3310. Min Act: -0.1700
Data Index: 1983155 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.3310. Min Act: -0.1700
Data Index: 4285728 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2998. Min Act: -0.1700
Data Index: 5528886 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2685. Min Act: -0.1700
Data Index: 8366504 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2685. Min Act: -0.1700
Data Index: 3856082 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2685. Min Act: -0.1700
Data Index: 1983156 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2685. Min Act: -0.1700
Data Index: 3205686 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2373. Min Act: -0.1700
Data Index: 4698979 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2685. Min Act: -0.1700
Data Index: 656350 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2373. Min Act: -0.1700
Data Index: 781248 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2685. Min Act: -0.1700
Data Index: 3043084 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.2060. Min Act: -0.1700
Data Index: 8456613 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.1748. Min Act: -0.1700
Data Index: 7939481 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.1748. Min Act: -0.1700
Data Index: 3428069 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.1748. Min Act: -0.1700
Data Index: 4698977 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.1748. Min Act: -0.1700
Data Index: 781249 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3935. Min Range: -7.3935
Max Act: 7.1748. Min Act: -0.1700
Data Index: 965127 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19