Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.7248. Min Act: -0.1700
Data Index: 4129075 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.6936. Min Act: -0.1700
Data Index: 5698061 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.4123. Min Act: -0.1700
Data Index: 5682095 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.3811. Min Act: -0.1700
Data Index: 8255817 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.3498. Min Act: -0.1700
Data Index: 1567753 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.2561. Min Act: -0.1700
Data Index: 5316734 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.2248. Min Act: -0.1700
Data Index: 3362045 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.2248. Min Act: -0.1700
Data Index: 2811254 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.2248. Min Act: -0.1700
Data Index: 971265 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1936. Min Act: -0.1700
Data Index: 3831971 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.2561. Min Act: -0.1700
Data Index: 5886084 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1936. Min Act: -0.1700
Data Index: 7397692 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1936. Min Act: -0.1700
Data Index: 5890492 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1936. Min Act: -0.1700
Data Index: 8688346 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1936. Min Act: -0.1700
Data Index: 1721284 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1936. Min Act: -0.1700
Data Index: 4447164 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1623. Min Act: -0.1700
Data Index: 3195665 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1936. Min Act: -0.1700
Data Index: 80613 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1623. Min Act: -0.1700
Data Index: 8686135 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7248. Min Range: -5.7248
Max Act: 5.1311. Min Act: -0.1700
Data Index: 5495895 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19