Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.4955. Min Act: -0.1700
Data Index: 6562912 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.4955. Min Act: -0.1700
Data Index: 3765843 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.3705. Min Act: -0.1700
Data Index: 2502758 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.3705. Min Act: -0.1700
Data Index: 901451 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.3705. Min Act: -0.1700
Data Index: 7838186 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.3080. Min Act: -0.1700
Data Index: 2004201 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.3080. Min Act: -0.1700
Data Index: 5499327 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.3080. Min Act: -0.1700
Data Index: 1510870 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.3080. Min Act: -0.1700
Data Index: 1842881 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.3080. Min Act: -0.1700
Data Index: 7431052 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.2455. Min Act: -0.1700
Data Index: 7032944 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.3080. Min Act: -0.1700
Data Index: 3337674 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.1830. Min Act: -0.1700
Data Index: 3285793 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.1830. Min Act: -0.1700
Data Index: 835332 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.1205. Min Act: -0.1700
Data Index: 2078744 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.1205. Min Act: -0.1700
Data Index: 3807532 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.1205. Min Act: -0.1700
Data Index: 3460274 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.1205. Min Act: -0.1700
Data Index: 116540 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.0580. Min Act: -0.1700
Data Index: 3790913 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4955. Min Range: -8.4955
Max Act: 8.0580. Min Act: -0.1700
Data Index: 6925907 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19