Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.2525. Min Act: -0.1700
Data Index: 6140931 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1588. Min Act: -0.1700
Data Index: 761683 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1588. Min Act: -0.1700
Data Index: 7652181 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1275. Min Act: -0.1700
Data Index: 4821053 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1275. Min Act: -0.1700
Data Index: 913575 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0338. Min Act: -0.1700
Data Index: 7128 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 4049389 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0338. Min Act: -0.1700
Data Index: 3450699 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 1215860 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 2880343 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 4821054 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 4606928 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 8421049 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 8288756 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9400. Min Act: -0.1700
Data Index: 8046193 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9400. Min Act: -0.1700
Data Index: 4696591 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 5914828 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9400. Min Act: -0.1700
Data Index: 3484136 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 1794447 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2525. Min Range: -5.2525
Max Act: 4.9713. Min Act: -0.1700
Data Index: 2628703 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19