Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2886 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2725. Min Range: -10.2725
Max Act: 10.2725. Min Act: -0.1700
Data Index: 153032 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2725. Min Range: -10.2725
Max Act: 10.2725. Min Act: -0.1700
Data Index: 2527137 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2725. Min Range: -10.2725
Max Act: 10.1475. Min Act: -0.1700
Data Index: 254793 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.9600. Min Act: -0.1700
Data Index: 772303 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.8975. Min Act: -0.1700
Data Index: 5930982 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.8350. Min Act: -0.1700
Data Index: 7984137 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.8350. Min Act: -0.1700
Data Index: 7679451 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.7725. Min Act: -0.1700
Data Index: 3940469 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.7725. Min Act: -0.1700
Data Index: 2343999 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.7725. Min Act: -0.1700
Data Index: 6562185 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.5850. Min Act: -0.1700
Data Index: 4075222 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.5850. Min Act: -0.1700
Data Index: 4679244 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.5225. Min Act: -0.1700
Data Index: 3024175 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.5225. Min Act: -0.1700
Data Index: 6584514 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.4600. Min Act: -0.1700
Data Index: 6083814 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.4600. Min Act: -0.1700
Data Index: 1844351 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.4600. Min Act: -0.1700
Data Index: 4746948 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.4600. Min Act: -0.1700
Data Index: 2706824 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.4600. Min Act: -0.1700
Data Index: 6271161 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2725. Min Range: -10.2725
Max Act: 9.4600. Min Act: -0.1700
Data Index: 3118630 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19