Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2235 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6887. Min Range: -7.6887
Max Act: 7.6887. Min Act: -0.1700
Data Index: 3555430 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.9387. Min Act: -0.1700
Data Index: 5502589 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.9074. Min Act: -0.1700
Data Index: 2559206 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.7824. Min Act: -0.1700
Data Index: 4644667 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.7824. Min Act: -0.1700
Data Index: 910106 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.7824. Min Act: -0.1700
Data Index: 370410 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.6887. Min Act: -0.1700
Data Index: 5827180 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.6574. Min Act: -0.1700
Data Index: 3130868 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.6574. Min Act: -0.1700
Data Index: 7385116 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.6262. Min Act: -0.1700
Data Index: 6965884 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.6262. Min Act: -0.1700
Data Index: 5141159 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.6262. Min Act: -0.1700
Data Index: 2855422 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.6262. Min Act: -0.1700
Data Index: 1600861 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.6262. Min Act: -0.1700
Data Index: 5393313 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.5949. Min Act: -0.1700
Data Index: 3790773 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.5637. Min Act: -0.1700
Data Index: 8688790 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.5637. Min Act: -0.1700
Data Index: 6772163 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.5637. Min Act: -0.1700
Data Index: 2280286 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.5637. Min Act: -0.1700
Data Index: 4159569 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6887. Min Range: -7.6887
Max Act: 6.5637. Min Act: -0.1700
Data Index: 7559960 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19