Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2559 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.6657. Min Act: -0.1700
Data Index: 5720663 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.6345. Min Act: -0.1700
Data Index: 465608 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.6345. Min Act: -0.1700
Data Index: 5760486 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.6032. Min Act: -0.1700
Data Index: 8690449 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.5095. Min Act: -0.1700
Data Index: 2547658 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.5407. Min Act: -0.1700
Data Index: 2744002 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.5095. Min Act: -0.1700
Data Index: 7358020 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.4782. Min Act: -0.1700
Data Index: 1720151 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.4782. Min Act: -0.1700
Data Index: 661688 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.4157. Min Act: -0.1700
Data Index: 3356587 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.3845. Min Act: -0.1700
Data Index: 3019913 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.3845. Min Act: -0.1700
Data Index: 4628165 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.3845. Min Act: -0.1700
Data Index: 6529786 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.3220. Min Act: -0.1700
Data Index: 1698905 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.2907. Min Act: -0.1700
Data Index: 3510730 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.2907. Min Act: -0.1700
Data Index: 4084272 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.2595. Min Act: -0.1700
Data Index: 5413925 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.2282. Min Act: -0.1700
Data Index: 3579730 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.2595. Min Act: -0.1700
Data Index: 6900484 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6657. Min Range: -5.6657
Max Act: 5.2282. Min Act: -0.1700
Data Index: 3488696 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19