Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5209 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1294. Min Range: -8.1294
Max Act: 8.1294. Min Act: -0.1700
Data Index: 4889776 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1294. Min Range: -8.1294
Max Act: 8.0669. Min Act: -0.1700
Data Index: 1655298 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.5357. Min Act: -0.1700
Data Index: 373673 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.5669. Min Act: -0.1700
Data Index: 2678805 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.3482. Min Act: -0.1700
Data Index: 4260034 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.2857. Min Act: -0.1700
Data Index: 1033892 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.2857. Min Act: -0.1700
Data Index: 4875743 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.2544. Min Act: -0.1700
Data Index: 4079504 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.2544. Min Act: -0.1700
Data Index: 1788450 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.1607. Min Act: -0.1700
Data Index: 8281681 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.1607. Min Act: -0.1700
Data Index: 8238681 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.1607. Min Act: -0.1700
Data Index: 46980 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.1294. Min Act: -0.1700
Data Index: 2459861 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.0669. Min Act: -0.1700
Data Index: 7874563 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.0982. Min Act: -0.1700
Data Index: 7351689 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.0982. Min Act: -0.1700
Data Index: 3440262 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.0357. Min Act: -0.1700
Data Index: 6385967 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.0357. Min Act: -0.1700
Data Index: 3157118 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.0357. Min Act: -0.1700
Data Index: 1575103 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1294. Min Range: -8.1294
Max Act: 7.0357. Min Act: -0.1700
Data Index: 597967 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19