Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3834 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.8165. Min Act: -0.1700
Data Index: 2220820 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 5182453 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 4061398 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.7540. Min Act: -0.1700
Data Index: 7613165 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.7228. Min Act: -0.1700
Data Index: 8816175 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.5353. Min Act: -0.1700
Data Index: 5317242 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.5353. Min Act: -0.1700
Data Index: 1770092 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.5040. Min Act: -0.1700
Data Index: 7841301 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.4728. Min Act: -0.1700
Data Index: 6363631 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.4103. Min Act: -0.1700
Data Index: 1599580 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.4103. Min Act: -0.1700
Data Index: 5170317 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.3165. Min Act: -0.1700
Data Index: 5817394 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.3165. Min Act: -0.1700
Data Index: 7719403 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.2853. Min Act: -0.1700
Data Index: 1172591 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.2853. Min Act: -0.1700
Data Index: 1147867 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.2853. Min Act: -0.1700
Data Index: 5926176 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.2853. Min Act: -0.1700
Data Index: 3043781 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.2540. Min Act: -0.1700
Data Index: 7140046 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.2540. Min Act: -0.1700
Data Index: 1130126 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8165. Min Range: -5.8165
Max Act: 5.2228. Min Act: -0.1700
Data Index: 357147 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19