Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2797 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0869. Min Range: -6.0869
Max Act: 6.0869. Min Act: -0.1700
Data Index: 1426264 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0869. Min Range: -6.0869
Max Act: 6.0869. Min Act: -0.1700
Data Index: 4734922 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.9619. Min Act: -0.1700
Data Index: 987204 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.8994. Min Act: -0.1700
Data Index: 6879346 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.8681. Min Act: -0.1700
Data Index: 3833076 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.8369. Min Act: -0.1700
Data Index: 3295915 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.8056. Min Act: -0.1700
Data Index: 1314021 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.7744. Min Act: -0.1700
Data Index: 6822364 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.7744. Min Act: -0.1700
Data Index: 5156053 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.7119. Min Act: -0.1700
Data Index: 6051962 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.6806. Min Act: -0.1700
Data Index: 955503 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.6806. Min Act: -0.1700
Data Index: 1046430 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.7119. Min Act: -0.1700
Data Index: 56351 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.6494. Min Act: -0.1700
Data Index: 3781443 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.5869. Min Act: -0.1700
Data Index: 4979957 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.6181. Min Act: -0.1700
Data Index: 2960766 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.6494. Min Act: -0.1700
Data Index: 2415502 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1993223 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.6181. Min Act: -0.1700
Data Index: 6570834 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0869. Min Range: -6.0869
Max Act: 5.5869. Min Act: -0.1700
Data Index: 4443609 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19