Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.6120. Min Act: -0.1700
Data Index: 2299458 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.4870. Min Act: -0.1700
Data Index: 8813241 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.4558. Min Act: -0.1700
Data Index: 851114 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.4245. Min Act: -0.1700
Data Index: 311600 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.4245. Min Act: -0.1700
Data Index: 491051 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.4245. Min Act: -0.1700
Data Index: 3057003 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.4245. Min Act: -0.1700
Data Index: 31209 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.3933. Min Act: -0.1700
Data Index: 5889228 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.3620. Min Act: -0.1700
Data Index: 5367724 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.3308. Min Act: -0.1700
Data Index: 2320388 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.3308. Min Act: -0.1700
Data Index: 5615709 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.2683. Min Act: -0.1700
Data Index: 2991338 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.2683. Min Act: -0.1700
Data Index: 8749960 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.2683. Min Act: -0.1700
Data Index: 192594 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.2058. Min Act: -0.1700
Data Index: 5411313 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.2370. Min Act: -0.1700
Data Index: 7759061 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.2058. Min Act: -0.1700
Data Index: 5395572 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.2058. Min Act: -0.1700
Data Index: 1379939 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.2058. Min Act: -0.1700
Data Index: 5921904 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6120. Min Range: -6.6120
Max Act: 6.2058. Min Act: -0.1700
Data Index: 675697 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19