Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3379. Min Range: -6.3379
Max Act: 6.3379. Min Act: -0.1700
Data Index: 5846829 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3379. Min Range: -6.3379
Max Act: 6.0254. Min Act: -0.1700
Data Index: 3674469 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.9942. Min Act: -0.1700
Data Index: 3683175 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.9629. Min Act: -0.1700
Data Index: 5207629 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.9317. Min Act: -0.1700
Data Index: 2536218 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.9004. Min Act: -0.1700
Data Index: 1669280 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.8379. Min Act: -0.1700
Data Index: 6120205 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7754. Min Act: -0.1700
Data Index: 8529408 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.8379. Min Act: -0.1700
Data Index: 2364387 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7754. Min Act: -0.1700
Data Index: 6222869 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7442. Min Act: -0.1700
Data Index: 748394 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7442. Min Act: -0.1700
Data Index: 1701664 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7754. Min Act: -0.1700
Data Index: 3645401 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7442. Min Act: -0.1700
Data Index: 5207632 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7442. Min Act: -0.1700
Data Index: 5243588 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7129. Min Act: -0.1700
Data Index: 88227 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7442. Min Act: -0.1700
Data Index: 3938976 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.6817. Min Act: -0.1700
Data Index: 264443 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.7442. Min Act: -0.1700
Data Index: 6326173 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3379. Min Range: -6.3379
Max Act: 5.6504. Min Act: -0.1700
Data Index: 2613879 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19