Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0348. Min Range: -5.0348
Max Act: 5.0036. Min Act: -0.1700
Data Index: 824708 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0348. Min Range: -5.0348
Max Act: 5.0348. Min Act: -0.1700
Data Index: 5158931 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.9723. Min Act: -0.1700
Data Index: 2162060 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.8786. Min Act: -0.1700
Data Index: 740736 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.8786. Min Act: -0.1700
Data Index: 4123931 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.8161. Min Act: -0.1700
Data Index: 3283647 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.8161. Min Act: -0.1700
Data Index: 8067091 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.7848. Min Act: -0.1700
Data Index: 7139509 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.7536. Min Act: -0.1700
Data Index: 752687 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.7223. Min Act: -0.1700
Data Index: 3965827 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.7223. Min Act: -0.1700
Data Index: 1057772 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.7223. Min Act: -0.1700
Data Index: 3899352 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.7223. Min Act: -0.1700
Data Index: 4386375 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.6911. Min Act: -0.1700
Data Index: 3974977 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.6911. Min Act: -0.1700
Data Index: 8427576 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.6911. Min Act: -0.1700
Data Index: 6548302 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.6598. Min Act: -0.1700
Data Index: 7375114 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.6598. Min Act: -0.1700
Data Index: 4022568 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.6286. Min Act: -0.1700
Data Index: 8415847 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0348. Min Range: -5.0348
Max Act: 4.6598. Min Act: -0.1700
Data Index: 4971855 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19