Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0030. Min Range: -10.0030
Max Act: 10.0030. Min Act: -0.1700
Data Index: 8571749 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.8155. Min Act: -0.1700
Data Index: 3533953 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.7530. Min Act: -0.1700
Data Index: 6121766 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.7530. Min Act: -0.1700
Data Index: 6109675 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.6905. Min Act: -0.1700
Data Index: 797987 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.6280. Min Act: -0.1700
Data Index: 7743129 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.6280. Min Act: -0.1700
Data Index: 6244039 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.5655. Min Act: -0.1700
Data Index: 3345332 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.5655. Min Act: -0.1700
Data Index: 8165849 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.5030. Min Act: -0.1700
Data Index: 7019408 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.5030. Min Act: -0.1700
Data Index: 1173418 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.3780. Min Act: -0.1700
Data Index: 2239444 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.3780. Min Act: -0.1700
Data Index: 6446571 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.3780. Min Act: -0.1700
Data Index: 2830591 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.3780. Min Act: -0.1700
Data Index: 5160564 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.3155. Min Act: -0.1700
Data Index: 5973322 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.3155. Min Act: -0.1700
Data Index: 6917756 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.3155. Min Act: -0.1700
Data Index: 7922580 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.3155. Min Act: -0.1700
Data Index: 5900442 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0030. Min Range: -10.0030
Max Act: 9.3155. Min Act: -0.1700
Data Index: 3133403 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19