Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4042 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.6742. Min Act: -0.1700
Data Index: 6203831 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.7680. Min Act: -0.1700
Data Index: 3869970 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.6117. Min Act: -0.1700
Data Index: 3783345 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.7055. Min Act: -0.1700
Data Index: 7971376 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.6742. Min Act: -0.1700
Data Index: 2913430 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.6117. Min Act: -0.1700
Data Index: 8002411 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.6117. Min Act: -0.1700
Data Index: 4233752 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.5492. Min Act: -0.1700
Data Index: 4329727 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.5492. Min Act: -0.1700
Data Index: 2475777 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.5180. Min Act: -0.1700
Data Index: 8656250 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.4867. Min Act: -0.1700
Data Index: 7040418 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.5492. Min Act: -0.1700
Data Index: 6541311 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.4867. Min Act: -0.1700
Data Index: 7593793 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.5180. Min Act: -0.1700
Data Index: 2387361 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.5492. Min Act: -0.1700
Data Index: 6225878 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.4867. Min Act: -0.1700
Data Index: 8357154 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.5492. Min Act: -0.1700
Data Index: 6333068 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.4867. Min Act: -0.1700
Data Index: 2372879 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.4555. Min Act: -0.1700
Data Index: 5768264 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7680. Min Range: -7.7680
Max Act: 7.4555. Min Act: -0.1700
Data Index: 4241300 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19