Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2827 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.8205. Min Act: -0.1700
Data Index: 1213634 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.6017. Min Act: -0.1700
Data Index: 669437 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.5080. Min Act: -0.1700
Data Index: 4962345 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.4142. Min Act: -0.1700
Data Index: 8404503 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.3830. Min Act: -0.1700
Data Index: 4631162 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.3205. Min Act: -0.1700
Data Index: 4163054 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.3517. Min Act: -0.1700
Data Index: 5105485 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.3517. Min Act: -0.1700
Data Index: 1906716 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.2892. Min Act: -0.1700
Data Index: 2565271 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.2892. Min Act: -0.1700
Data Index: 3275352 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.2580. Min Act: -0.1700
Data Index: 6583107 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.2267. Min Act: -0.1700
Data Index: 669441 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.1954. Min Act: -0.1700
Data Index: 1254990 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.1954. Min Act: -0.1700
Data Index: 5489036 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.1017. Min Act: -0.1700
Data Index: 669440 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.1017. Min Act: -0.1700
Data Index: 7591271 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.1329. Min Act: -0.1700
Data Index: 6651701 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.1017. Min Act: -0.1700
Data Index: 620487 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.1017. Min Act: -0.1700
Data Index: 2188497 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8205. Min Range: -4.8205
Max Act: 4.1017. Min Act: -0.1700
Data Index: 472934 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19