Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4121. Min Range: -8.4121
Max Act: 8.4121. Min Act: -0.1700
Data Index: 1748568 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4121. Min Range: -8.4121
Max Act: 8.4121. Min Act: -0.1700
Data Index: 3175335 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4121. Min Range: -8.4121
Max Act: 8.3496. Min Act: -0.1700
Data Index: 5060288 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4121. Min Range: -8.4121
Max Act: 8.2246. Min Act: -0.1700
Data Index: 6406388 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4121. Min Range: -8.4121
Max Act: 8.0996. Min Act: -0.1700
Data Index: 3428441 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4121. Min Range: -8.4121
Max Act: 8.0371. Min Act: -0.1700
Data Index: 3484382 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.9121. Min Act: -0.1700
Data Index: 3839703 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.8496. Min Act: -0.1700
Data Index: 8314086 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.7871. Min Act: -0.1700
Data Index: 4337970 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.7871. Min Act: -0.1700
Data Index: 8083897 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.7871. Min Act: -0.1700
Data Index: 2895089 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.6621. Min Act: -0.1700
Data Index: 2162905 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.7246. Min Act: -0.1700
Data Index: 847464 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.5996. Min Act: -0.1700
Data Index: 4918980 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.7246. Min Act: -0.1700
Data Index: 6519075 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.6621. Min Act: -0.1700
Data Index: 3612278 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.7246. Min Act: -0.1700
Data Index: 2794688 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.6621. Min Act: -0.1700
Data Index: 8754776 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.5996. Min Act: -0.1700
Data Index: 7737939 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4121. Min Range: -8.4121
Max Act: 7.5996. Min Act: -0.1700
Data Index: 4309008 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19