Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2377 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5418. Min Range: -8.5418
Max Act: 8.5418. Min Act: -0.1700
Data Index: 6238446 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.9793. Min Act: -0.1700
Data Index: 4173487 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.9481. Min Act: -0.1700
Data Index: 6580557 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.8231. Min Act: -0.1700
Data Index: 4036255 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.8231. Min Act: -0.1700
Data Index: 3277294 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.6668. Min Act: -0.1700
Data Index: 573048 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.6356. Min Act: -0.1700
Data Index: 7066888 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.6356. Min Act: -0.1700
Data Index: 8793650 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.5731. Min Act: -0.1700
Data Index: 265199 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.5731. Min Act: -0.1700
Data Index: 7268701 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.5418. Min Act: -0.1700
Data Index: 2186628 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.5731. Min Act: -0.1700
Data Index: 5565732 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.4793. Min Act: -0.1700
Data Index: 6794900 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.4793. Min Act: -0.1700
Data Index: 4197264 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.4793. Min Act: -0.1700
Data Index: 4930367 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.4793. Min Act: -0.1700
Data Index: 7268699 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.4481. Min Act: -0.1700
Data Index: 3003434 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.4168. Min Act: -0.1700
Data Index: 4522520 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.3543. Min Act: -0.1700
Data Index: 81234 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5418. Min Range: -8.5418
Max Act: 7.3856. Min Act: -0.1700
Data Index: 7087679 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19