Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4392 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.6065. Min Act: -0.1700
Data Index: 1581234 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3877. Min Act: -0.1700
Data Index: 1394628 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3877. Min Act: -0.1700
Data Index: 2006274 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.4190. Min Act: -0.1700
Data Index: 528196 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3877. Min Act: -0.1700
Data Index: 7596227 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3877. Min Act: -0.1700
Data Index: 2401933 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3877. Min Act: -0.1700
Data Index: 1650533 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3565. Min Act: -0.1700
Data Index: 7197755 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3252. Min Act: -0.1700
Data Index: 6355124 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3252. Min Act: -0.1700
Data Index: 1511168 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3252. Min Act: -0.1700
Data Index: 6550559 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.3252. Min Act: -0.1700
Data Index: 3465218 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.2627. Min Act: -0.1700
Data Index: 5978715 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.2940. Min Act: -0.1700
Data Index: 437507 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.2940. Min Act: -0.1700
Data Index: 2757255 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.2940. Min Act: -0.1700
Data Index: 7107295 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.2627. Min Act: -0.1700
Data Index: 500758 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.2627. Min Act: -0.1700
Data Index: 6679366 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.2627. Min Act: -0.1700
Data Index: 2323891 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6065. Min Range: -5.6065
Max Act: 5.2627. Min Act: -0.1700
Data Index: 1826124 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19