Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1199. Min Range: -6.1199
Max Act: 6.1199. Min Act: -0.1700
Data Index: 7447108 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.8699. Min Act: -0.1700
Data Index: 5314015 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.8387. Min Act: -0.1700
Data Index: 5799660 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.7137. Min Act: -0.1700
Data Index: 1191611 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.6512. Min Act: -0.1700
Data Index: 5090656 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.6512. Min Act: -0.1700
Data Index: 5935677 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.5887. Min Act: -0.1700
Data Index: 1855031 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.5887. Min Act: -0.1700
Data Index: 4875308 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.5887. Min Act: -0.1700
Data Index: 3177722 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.5574. Min Act: -0.1700
Data Index: 3209452 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.5574. Min Act: -0.1700
Data Index: 3607533 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.5574. Min Act: -0.1700
Data Index: 4281177 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.5262. Min Act: -0.1700
Data Index: 131285 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.5262. Min Act: -0.1700
Data Index: 2203084 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.5262. Min Act: -0.1700
Data Index: 3873714 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.4949. Min Act: -0.1700
Data Index: 5965829 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.4637. Min Act: -0.1700
Data Index: 1056655 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.4324. Min Act: -0.1700
Data Index: 638045 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.4324. Min Act: -0.1700
Data Index: 3226432 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1199. Min Range: -6.1199
Max Act: 5.4012. Min Act: -0.1700
Data Index: 5794816 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19