Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4135 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5192. Min Range: -10.5192
Max Act: 10.5192. Min Act: -0.1700
Data Index: 7262745 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5192. Min Range: -10.5192
Max Act: 10.2067. Min Act: -0.1700
Data Index: 6421461 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5192. Min Range: -10.5192
Max Act: 10.0192. Min Act: -0.1700
Data Index: 7021951 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.9567. Min Act: -0.1700
Data Index: 2489999 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.7692. Min Act: -0.1700
Data Index: 1631853 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.8317. Min Act: -0.1700
Data Index: 819157 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.7692. Min Act: -0.1700
Data Index: 7473033 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.7692. Min Act: -0.1700
Data Index: 8241886 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.7692. Min Act: -0.1700
Data Index: 5887575 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.7692. Min Act: -0.1700
Data Index: 790355 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.7067. Min Act: -0.1700
Data Index: 441968 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.7067. Min Act: -0.1700
Data Index: 8347047 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.7067. Min Act: -0.1700
Data Index: 1530056 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.6442. Min Act: -0.1700
Data Index: 940648 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.5817. Min Act: -0.1700
Data Index: 4220098 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.5817. Min Act: -0.1700
Data Index: 1545126 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.5817. Min Act: -0.1700
Data Index: 5189205 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.5817. Min Act: -0.1700
Data Index: 1853615 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.5817. Min Act: -0.1700
Data Index: 7629810 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5192. Min Range: -10.5192
Max Act: 9.5192. Min Act: -0.1700
Data Index: 2392582 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19