Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 916 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1080. Min Range: -5.1080
Max Act: 5.1080. Min Act: -0.1700
Data Index: 3217501 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1080. Min Range: -5.1080
Max Act: 5.0455. Min Act: -0.1700
Data Index: 8379130 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1080. Min Range: -5.1080
Max Act: 5.0455. Min Act: -0.1700
Data Index: 986880 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1080. Min Range: -5.1080
Max Act: 5.0768. Min Act: -0.1700
Data Index: 5232678 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1080. Min Range: -5.1080
Max Act: 5.0143. Min Act: -0.1700
Data Index: 6409752 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.9830. Min Act: -0.1700
Data Index: 5684985 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.9518. Min Act: -0.1700
Data Index: 3119113 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.9518. Min Act: -0.1700
Data Index: 5684984 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.9518. Min Act: -0.1700
Data Index: 3431836 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.9205. Min Act: -0.1700
Data Index: 3000376 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.9205. Min Act: -0.1700
Data Index: 4851781 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.9205. Min Act: -0.1700
Data Index: 2793736 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.9205. Min Act: -0.1700
Data Index: 3695775 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.8893. Min Act: -0.1700
Data Index: 2940062 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.8580. Min Act: -0.1700
Data Index: 4179653 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.8580. Min Act: -0.1700
Data Index: 225255 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.8580. Min Act: -0.1700
Data Index: 3695776 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.8580. Min Act: -0.1700
Data Index: 6965312 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.8893. Min Act: -0.1700
Data Index: 3918837 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1080. Min Range: -5.1080
Max Act: 4.7955. Min Act: -0.1700
Data Index: 26155 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19