Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3063 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.8940. Min Act: -0.1700
Data Index: 7834028 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.7690. Min Act: -0.1700
Data Index: 4812179 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.8003. Min Act: -0.1700
Data Index: 2659306 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.7378. Min Act: -0.1700
Data Index: 1660547 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.7378. Min Act: -0.1700
Data Index: 1434190 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.7065. Min Act: -0.1700
Data Index: 6781447 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.7065. Min Act: -0.1700
Data Index: 606575 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6753. Min Act: -0.1700
Data Index: 7217423 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.7065. Min Act: -0.1700
Data Index: 6279000 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6753. Min Act: -0.1700
Data Index: 2659305 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6753. Min Act: -0.1700
Data Index: 397899 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6440. Min Act: -0.1700
Data Index: 8385555 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6440. Min Act: -0.1700
Data Index: 3545060 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6440. Min Act: -0.1700
Data Index: 7196855 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.5815. Min Act: -0.1700
Data Index: 7541800 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6128. Min Act: -0.1700
Data Index: 5975972 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6128. Min Act: -0.1700
Data Index: 7885861 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6128. Min Act: -0.1700
Data Index: 2916171 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.5815. Min Act: -0.1700
Data Index: 385818 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8940. Min Range: -5.8940
Max Act: 5.6128. Min Act: -0.1700
Data Index: 2180812 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19