Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3430 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.9093. Min Act: -0.1700
Data Index: 5946692 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.7843. Min Act: -0.1700
Data Index: 1832547 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.7218. Min Act: -0.1700
Data Index: 8116927 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.7218. Min Act: -0.1700
Data Index: 7135455 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.6593. Min Act: -0.1700
Data Index: 3239328 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.6593. Min Act: -0.1700
Data Index: 6956037 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.6280. Min Act: -0.1700
Data Index: 6138541 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.6280. Min Act: -0.1700
Data Index: 6167789 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.5655. Min Act: -0.1700
Data Index: 250986 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.5655. Min Act: -0.1700
Data Index: 7955032 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.5655. Min Act: -0.1700
Data Index: 4727682 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.5343. Min Act: -0.1700
Data Index: 28934 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.5030. Min Act: -0.1700
Data Index: 4727683 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.4718. Min Act: -0.1700
Data Index: 7236781 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.4093. Min Act: -0.1700
Data Index: 4566527 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.3468. Min Act: -0.1700
Data Index: 7566449 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.3468. Min Act: -0.1700
Data Index: 6935668 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.3468. Min Act: -0.1700
Data Index: 4014537 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.3155. Min Act: -0.1700
Data Index: 1058620 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9093. Min Range: -7.9093
Max Act: 7.2530. Min Act: -0.1700
Data Index: 2529684 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19