Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 555 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.7874. Min Act: -0.1700
Data Index: 8597744 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.7249. Min Act: -0.1700
Data Index: 6741741 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.7249. Min Act: -0.1700
Data Index: 8697499 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.5687. Min Act: -0.1700
Data Index: 2194458 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.5374. Min Act: -0.1700
Data Index: 4093287 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.5374. Min Act: -0.1700
Data Index: 1687684 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.4749. Min Act: -0.1700
Data Index: 749721 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.4437. Min Act: -0.1700
Data Index: 7122810 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.4437. Min Act: -0.1700
Data Index: 8295549 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.4124. Min Act: -0.1700
Data Index: 1699804 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.4124. Min Act: -0.1700
Data Index: 8412858 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.4124. Min Act: -0.1700
Data Index: 6099735 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.4124. Min Act: -0.1700
Data Index: 8363125 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.4124. Min Act: -0.1700
Data Index: 7169712 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.3499. Min Act: -0.1700
Data Index: 673542 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.3499. Min Act: -0.1700
Data Index: 8569716 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.2874. Min Act: -0.1700
Data Index: 8681929 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.3187. Min Act: -0.1700
Data Index: 6977972 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.3187. Min Act: -0.1700
Data Index: 2946665 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7874. Min Range: -7.7874
Max Act: 7.2874. Min Act: -0.1700
Data Index: 2478773 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19