Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6205 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.1027. Min Act: -0.1700
Data Index: 446325 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.1027. Min Act: -0.1700
Data Index: 3729066 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.0714. Min Act: -0.1700
Data Index: 7384666 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.1027. Min Act: -0.1700
Data Index: 7069206 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.0714. Min Act: -0.1700
Data Index: 790913 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.0402. Min Act: -0.1700
Data Index: 2668779 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.0089. Min Act: -0.1700
Data Index: 3905339 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.0089. Min Act: -0.1700
Data Index: 4086091 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.0089. Min Act: -0.1700
Data Index: 8234798 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1027. Min Range: -5.1027
Max Act: 5.0089. Min Act: -0.1700
Data Index: 4932932 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.9777. Min Act: -0.1700
Data Index: 2963526 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.9777. Min Act: -0.1700
Data Index: 3708315 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.9464. Min Act: -0.1700
Data Index: 2678887 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.9152. Min Act: -0.1700
Data Index: 5763874 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.8839. Min Act: -0.1700
Data Index: 8325302 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.8214. Min Act: -0.1700
Data Index: 3932179 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.8214. Min Act: -0.1700
Data Index: 851229 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.8214. Min Act: -0.1700
Data Index: 7085872 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.8214. Min Act: -0.1700
Data Index: 4125809 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1027. Min Range: -5.1027
Max Act: 4.8214. Min Act: -0.1700
Data Index: 5984888 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19