Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2417 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.7262. Min Act: -0.1700
Data Index: 2110268 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.5699. Min Act: -0.1700
Data Index: 2400712 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.4449. Min Act: -0.1700
Data Index: 835628 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.4137. Min Act: -0.1700
Data Index: 6644497 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.3512. Min Act: -0.1700
Data Index: 3335024 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.3199. Min Act: -0.1700
Data Index: 2575900 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.2887. Min Act: -0.1700
Data Index: 4702775 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.1949. Min Act: -0.1700
Data Index: 8753011 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.1324. Min Act: -0.1700
Data Index: 5406442 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.1324. Min Act: -0.1700
Data Index: 2365849 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.0699. Min Act: -0.1700
Data Index: 1885341 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.0387. Min Act: -0.1700
Data Index: 7237130 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.0074. Min Act: -0.1700
Data Index: 1665738 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.0074. Min Act: -0.1700
Data Index: 89649 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.0074. Min Act: -0.1700
Data Index: 7715549 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7262. Min Range: -7.7262
Max Act: 7.0074. Min Act: -0.1700
Data Index: 4494579 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7262. Min Range: -7.7262
Max Act: 6.9762. Min Act: -0.1700
Data Index: 4648087 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7262. Min Range: -7.7262
Max Act: 6.9449. Min Act: -0.1700
Data Index: 2931248 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7262. Min Range: -7.7262
Max Act: 6.9449. Min Act: -0.1700
Data Index: 7994812 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7262. Min Range: -7.7262
Max Act: 6.9449. Min Act: -0.1700
Data Index: 6149296 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19