Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1121 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4718. Min Range: -8.4718
Max Act: 8.4718. Min Act: -0.1700
Data Index: 6704880 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4718. Min Range: -8.4718
Max Act: 8.2218. Min Act: -0.1700
Data Index: 322406 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4718. Min Range: -8.4718
Max Act: 8.2218. Min Act: -0.1700
Data Index: 8003752 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4718. Min Range: -8.4718
Max Act: 8.0655. Min Act: -0.1700
Data Index: 3391362 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4718. Min Range: -8.4718
Max Act: 8.0343. Min Act: -0.1700
Data Index: 541123 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4718. Min Range: -8.4718
Max Act: 8.0030. Min Act: -0.1700
Data Index: 7433072 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4718. Min Range: -8.4718
Max Act: 8.0343. Min Act: -0.1700
Data Index: 8623403 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4718. Min Range: -8.4718
Max Act: 8.0030. Min Act: -0.1700
Data Index: 4747679 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.9718. Min Act: -0.1700
Data Index: 785378 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.8780. Min Act: -0.1700
Data Index: 6040981 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.8468. Min Act: -0.1700
Data Index: 6052668 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.7843. Min Act: -0.1700
Data Index: 3537674 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.8155. Min Act: -0.1700
Data Index: 1747068 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.7843. Min Act: -0.1700
Data Index: 8619819 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.7530. Min Act: -0.1700
Data Index: 7459023 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.8155. Min Act: -0.1700
Data Index: 178084 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.7530. Min Act: -0.1700
Data Index: 1565128 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.7530. Min Act: -0.1700
Data Index: 4719205 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.7218. Min Act: -0.1700
Data Index: 8099389 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4718. Min Range: -8.4718
Max Act: 7.6905. Min Act: -0.1700
Data Index: 7619753 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19