Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.2698. Min Act: -0.1700
Data Index: 4651324 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.2698. Min Act: -0.1700
Data Index: 6181500 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.2698. Min Act: -0.1700
Data Index: 3626101 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.2386. Min Act: -0.1700
Data Index: 6101446 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.2073. Min Act: -0.1700
Data Index: 6831733 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.2073. Min Act: -0.1700
Data Index: 5894750 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.2386. Min Act: -0.1700
Data Index: 5842203 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.2073. Min Act: -0.1700
Data Index: 420135 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1448. Min Act: -0.1700
Data Index: 420134 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.2073. Min Act: -0.1700
Data Index: 5865145 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1448. Min Act: -0.1700
Data Index: 5842204 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1761. Min Act: -0.1700
Data Index: 6190913 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1761. Min Act: -0.1700
Data Index: 2043520 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1761. Min Act: -0.1700
Data Index: 5484862 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1136. Min Act: -0.1700
Data Index: 6101447 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1448. Min Act: -0.1700
Data Index: 6831732 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1136. Min Act: -0.1700
Data Index: 7664063 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1448. Min Act: -0.1700
Data Index: 3213922 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1136. Min Act: -0.1700
Data Index: 2043519 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2698. Min Range: -8.2698
Max Act: 8.1136. Min Act: -0.1700
Data Index: 6181501 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19