Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1554 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0841. Min Range: -5.0841
Max Act: 5.0841. Min Act: -0.1700
Data Index: 1999660 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.7716. Min Act: -0.1700
Data Index: 2232621 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.7404. Min Act: -0.1700
Data Index: 2793021 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.7404. Min Act: -0.1700
Data Index: 3542180 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.6466. Min Act: -0.1700
Data Index: 3094310 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.6466. Min Act: -0.1700
Data Index: 2597047 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.6154. Min Act: -0.1700
Data Index: 2171048 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.6154. Min Act: -0.1700
Data Index: 4096886 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5841. Min Act: -0.1700
Data Index: 2116529 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5841. Min Act: -0.1700
Data Index: 5661544 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5841. Min Act: -0.1700
Data Index: 2271390 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5841. Min Act: -0.1700
Data Index: 6266797 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5841. Min Act: -0.1700
Data Index: 4339508 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5216. Min Act: -0.1700
Data Index: 5173977 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5529. Min Act: -0.1700
Data Index: 5225362 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5529. Min Act: -0.1700
Data Index: 1797611 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5529. Min Act: -0.1700
Data Index: 4135839 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5529. Min Act: -0.1700
Data Index: 3624763 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5529. Min Act: -0.1700
Data Index: 5799143 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0841. Min Range: -5.0841
Max Act: 4.5529. Min Act: -0.1700
Data Index: 937405 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19