Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 863 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.4163. Min Act: -0.1700
Data Index: 4330084 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.2600. Min Act: -0.1700
Data Index: 3726686 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.2913. Min Act: -0.1700
Data Index: 2103150 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.2288. Min Act: -0.1700
Data Index: 6048183 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.1663. Min Act: -0.1700
Data Index: 731380 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.1038. Min Act: -0.1700
Data Index: 4110938 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.0725. Min Act: -0.1700
Data Index: 6988740 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.0725. Min Act: -0.1700
Data Index: 495891 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.0100. Min Act: -0.1700
Data Index: 3378870 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.9788. Min Act: -0.1700
Data Index: 3109039 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4163. Min Range: -7.4163
Max Act: 7.0100. Min Act: -0.1700
Data Index: 8425016 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.9788. Min Act: -0.1700
Data Index: 2117446 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.9788. Min Act: -0.1700
Data Index: 2643098 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.9788. Min Act: -0.1700
Data Index: 5190333 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.9475. Min Act: -0.1700
Data Index: 3539914 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.9475. Min Act: -0.1700
Data Index: 4321253 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.9163. Min Act: -0.1700
Data Index: 2376554 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.9163. Min Act: -0.1700
Data Index: 1751008 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.9163. Min Act: -0.1700
Data Index: 5136270 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4163. Min Range: -7.4163
Max Act: 6.8850. Min Act: -0.1700
Data Index: 5361684 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19