Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1080 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.9806. Min Act: -0.1700
Data Index: 3036380 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0119. Min Range: -4.0119
Max Act: 4.0119. Min Act: -0.1700
Data Index: 145052 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.8868. Min Act: -0.1700
Data Index: 8708818 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.8868. Min Act: -0.1700
Data Index: 8171264 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.8555. Min Act: -0.1700
Data Index: 2213314 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7930. Min Act: -0.1700
Data Index: 7322602 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.8243. Min Act: -0.1700
Data Index: 2036786 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.8243. Min Act: -0.1700
Data Index: 7684592 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.8243. Min Act: -0.1700
Data Index: 5314096 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7930. Min Act: -0.1700
Data Index: 2613113 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7930. Min Act: -0.1700
Data Index: 723656 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7930. Min Act: -0.1700
Data Index: 7785915 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7930. Min Act: -0.1700
Data Index: 655348 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7930. Min Act: -0.1700
Data Index: 6075115 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7617. Min Act: -0.1700
Data Index: 8330763 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7617. Min Act: -0.1700
Data Index: 7118644 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7617. Min Act: -0.1700
Data Index: 1034797 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7617. Min Act: -0.1700
Data Index: 2884359 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7617. Min Act: -0.1700
Data Index: 7205810 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0119. Min Range: -4.0119
Max Act: 3.7617. Min Act: -0.1700
Data Index: 4060314 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19