Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1760 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0636. Min Range: -7.0636
Max Act: 7.0324. Min Act: -0.1700
Data Index: 7388988 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0636. Min Range: -7.0636
Max Act: 7.0636. Min Act: -0.1700
Data Index: 1274127 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.9699. Min Act: -0.1700
Data Index: 7061298 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.8449. Min Act: -0.1700
Data Index: 5428199 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.8449. Min Act: -0.1700
Data Index: 7830306 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.7824. Min Act: -0.1700
Data Index: 1037828 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.7511. Min Act: -0.1700
Data Index: 6899984 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.7199. Min Act: -0.1700
Data Index: 6484817 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.6886. Min Act: -0.1700
Data Index: 5248468 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.6574. Min Act: -0.1700
Data Index: 2194947 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.6886. Min Act: -0.1700
Data Index: 4962022 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.5949. Min Act: -0.1700
Data Index: 4572184 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.6261. Min Act: -0.1700
Data Index: 1950762 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.6261. Min Act: -0.1700
Data Index: 8143262 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.5949. Min Act: -0.1700
Data Index: 5774096 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.5949. Min Act: -0.1700
Data Index: 1470842 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.5949. Min Act: -0.1700
Data Index: 2808844 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.5949. Min Act: -0.1700
Data Index: 5024642 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.5636. Min Act: -0.1700
Data Index: 1526544 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0636. Min Range: -7.0636
Max Act: 6.5324. Min Act: -0.1700
Data Index: 6991992 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19