Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2845 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.0927. Min Range: -13.0927
Max Act: 13.0927. Min Act: -0.1700
Data Index: 4351533 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.0927. Min Range: -13.0927
Max Act: 12.5302. Min Act: -0.1700
Data Index: 1270890 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.0927. Min Range: -13.0927
Max Act: 12.4677. Min Act: -0.1700
Data Index: 7918502 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.0927. Min Range: -13.0927
Max Act: 12.2177. Min Act: -0.1700
Data Index: 1398418 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.0927. Min Range: -13.0927
Max Act: 12.2177. Min Act: -0.1700
Data Index: 7088945 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.0927. Min Range: -13.0927
Max Act: 12.1552. Min Act: -0.1700
Data Index: 4959479 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.8427. Min Act: -0.1700
Data Index: 3570632 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.6552. Min Act: -0.1700
Data Index: 4600950 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.5927. Min Act: -0.1700
Data Index: 5962181 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.5927. Min Act: -0.1700
Data Index: 4329398 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.5302. Min Act: -0.1700
Data Index: 7918516 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.5302. Min Act: -0.1700
Data Index: 1655707 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.5302. Min Act: -0.1700
Data Index: 8255072 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.5302. Min Act: -0.1700
Data Index: 1727484 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.4052. Min Act: -0.1700
Data Index: 7532876 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.4677. Min Act: -0.1700
Data Index: 153554 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.4677. Min Act: -0.1700
Data Index: 3560726 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.4052. Min Act: -0.1700
Data Index: 2983668 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.4052. Min Act: -0.1700
Data Index: 310487 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.0927. Min Range: -13.0927
Max Act: 11.4677. Min Act: -0.1700
Data Index: 478713 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19