Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5028 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.3017. Min Act: -0.1700
Data Index: 6835223 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.2079. Min Act: -0.1700
Data Index: 2584924 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1700
Data Index: 3423929 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1700
Data Index: 4863210 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1767. Min Act: -0.1700
Data Index: 2574390 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1142. Min Act: -0.1700
Data Index: 4656285 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1454. Min Act: -0.1700
Data Index: 6538355 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1142. Min Act: -0.1700
Data Index: 4811292 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1454. Min Act: -0.1700
Data Index: 755015 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1142. Min Act: -0.1700
Data Index: 7956527 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.0829. Min Act: -0.1700
Data Index: 5361508 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1142. Min Act: -0.1700
Data Index: 6415557 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1142. Min Act: -0.1700
Data Index: 3031657 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.0829. Min Act: -0.1700
Data Index: 5344149 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.1142. Min Act: -0.1700
Data Index: 8816959 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.0829. Min Act: -0.1700
Data Index: 5678085 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.0829. Min Act: -0.1700
Data Index: 182131 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.0829. Min Act: -0.1700
Data Index: 222443 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.0829. Min Act: -0.1700
Data Index: 7880642 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3017. Min Range: -5.3017
Max Act: 5.0829. Min Act: -0.1700
Data Index: 3078015 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19