Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2974 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.7508. Min Act: -0.1700
Data Index: 7181476 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.3758. Min Act: -0.1700
Data Index: 3082514 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.1883. Min Act: -0.1700
Data Index: 1877421 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.1883. Min Act: -0.1700
Data Index: 935373 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.1258. Min Act: -0.1700
Data Index: 6729794 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.0633. Min Act: -0.1700
Data Index: 1759226 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.0633. Min Act: -0.1700
Data Index: 4490303 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.0008. Min Act: -0.1700
Data Index: 5825894 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.0008. Min Act: -0.1700
Data Index: 3459127 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7508. Min Range: -10.7508
Max Act: 10.0008. Min Act: -0.1700
Data Index: 2964840 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.9383. Min Act: -0.1700
Data Index: 8782230 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.9383. Min Act: -0.1700
Data Index: 3400386 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.9383. Min Act: -0.1700
Data Index: 3613587 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.8758. Min Act: -0.1700
Data Index: 8051539 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.8758. Min Act: -0.1700
Data Index: 551168 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.8133. Min Act: -0.1700
Data Index: 7863399 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.8133. Min Act: -0.1700
Data Index: 4135642 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.7508. Min Act: -0.1700
Data Index: 2583982 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.7508. Min Act: -0.1700
Data Index: 1297077 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7508. Min Range: -10.7508
Max Act: 9.7508. Min Act: -0.1700
Data Index: 5066723 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19