Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.8884. Min Act: -0.1700
Data Index: 296620 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.8259. Min Act: -0.1700
Data Index: 3315077 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.7634. Min Act: -0.1700
Data Index: 5371008 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.7947. Min Act: -0.1700
Data Index: 6788631 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.7634. Min Act: -0.1700
Data Index: 5291745 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.7634. Min Act: -0.1700
Data Index: 6708861 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.6384. Min Act: -0.1700
Data Index: 4764502 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.6384. Min Act: -0.1700
Data Index: 6749218 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5759. Min Act: -0.1700
Data Index: 1844176 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.6072. Min Act: -0.1700
Data Index: 3139742 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5759. Min Act: -0.1700
Data Index: 4429415 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5447. Min Act: -0.1700
Data Index: 2889057 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5447. Min Act: -0.1700
Data Index: 189649 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5759. Min Act: -0.1700
Data Index: 153886 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.6072. Min Act: -0.1700
Data Index: 1682193 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5759. Min Act: -0.1700
Data Index: 8417417 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5759. Min Act: -0.1700
Data Index: 5433169 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5759. Min Act: -0.1700
Data Index: 5542129 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5447. Min Act: -0.1700
Data Index: 2083733 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8884. Min Range: -5.8884
Max Act: 5.5447. Min Act: -0.1700
Data Index: 2810407 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19