Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4044 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.8687. Min Act: -0.1700
Data Index: 4838821 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.8687. Min Act: -0.1700
Data Index: 2034260 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.8062. Min Act: -0.1700
Data Index: 1931130 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.8062. Min Act: -0.1700
Data Index: 7807849 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7437. Min Act: -0.1700
Data Index: 2630892 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7750. Min Act: -0.1700
Data Index: 2371395 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7437. Min Act: -0.1700
Data Index: 3542951 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7437. Min Act: -0.1700
Data Index: 5481870 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7437. Min Act: -0.1700
Data Index: 5784161 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7437. Min Act: -0.1700
Data Index: 5696347 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7437. Min Act: -0.1700
Data Index: 1722850 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7125. Min Act: -0.1700
Data Index: 6648813 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7125. Min Act: -0.1700
Data Index: 7343432 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.6812. Min Act: -0.1700
Data Index: 1897729 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.6812. Min Act: -0.1700
Data Index: 1323260 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.6812. Min Act: -0.1700
Data Index: 2442189 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.7125. Min Act: -0.1700
Data Index: 518350 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.6812. Min Act: -0.1700
Data Index: 335947 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.6812. Min Act: -0.1700
Data Index: 1982693 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8687. Min Range: -4.8687
Max Act: 4.6812. Min Act: -0.1700
Data Index: 4717238 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19