Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2713 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0299. Min Range: -5.0299
Max Act: 5.0299. Min Act: -0.1700
Data Index: 215784 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.8111. Min Act: -0.1700
Data Index: 5001230 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.8111. Min Act: -0.1700
Data Index: 4481320 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.8111. Min Act: -0.1700
Data Index: 3437628 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7799. Min Act: -0.1700
Data Index: 2807816 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 7655377 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 158956 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.7486. Min Act: -0.1700
Data Index: 7291513 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.6236. Min Act: -0.1700
Data Index: 3501978 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5924. Min Act: -0.1700
Data Index: 2161575 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5924. Min Act: -0.1700
Data Index: 5017557 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5924. Min Act: -0.1700
Data Index: 616429 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5924. Min Act: -0.1700
Data Index: 8518504 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5924. Min Act: -0.1700
Data Index: 4731864 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5611. Min Act: -0.1700
Data Index: 596155 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5611. Min Act: -0.1700
Data Index: 31700 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5611. Min Act: -0.1700
Data Index: 7444196 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5299. Min Act: -0.1700
Data Index: 4481324 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5611. Min Act: -0.1700
Data Index: 4782268 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0299. Min Range: -5.0299
Max Act: 4.5299. Min Act: -0.1700
Data Index: 6795376 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19