Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5723 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.7937. Min Act: -0.1700
Data Index: 5699780 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.7624. Min Act: -0.1700
Data Index: 6323242 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.7312. Min Act: -0.1700
Data Index: 5462681 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.6062. Min Act: -0.1700
Data Index: 5481690 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.5749. Min Act: -0.1700
Data Index: 538133 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.5437. Min Act: -0.1700
Data Index: 7552363 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.5124. Min Act: -0.1700
Data Index: 8808543 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.4812. Min Act: -0.1700
Data Index: 4792350 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.4499. Min Act: -0.1700
Data Index: 6210065 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.4499. Min Act: -0.1700
Data Index: 2407983 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.4187. Min Act: -0.1700
Data Index: 1584568 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.3874. Min Act: -0.1700
Data Index: 7787926 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.3249. Min Act: -0.1700
Data Index: 6443859 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.3249. Min Act: -0.1700
Data Index: 7019344 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.3249. Min Act: -0.1700
Data Index: 2721027 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.3562. Min Act: -0.1700
Data Index: 2350226 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.3249. Min Act: -0.1700
Data Index: 6427534 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.3249. Min Act: -0.1700
Data Index: 2804445 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.2937. Min Act: -0.1700
Data Index: 4264857 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7937. Min Range: -5.7937
Max Act: 5.2937. Min Act: -0.1700
Data Index: 6692394 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19