Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5368. Min Range: -7.5368
Max Act: 7.5368. Min Act: -0.1700
Data Index: 2286973 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5368. Min Range: -7.5368
Max Act: 7.5368. Min Act: -0.1700
Data Index: 8782266 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5368. Min Range: -7.5368
Max Act: 7.4118. Min Act: -0.1700
Data Index: 6609096 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5368. Min Range: -7.5368
Max Act: 7.1618. Min Act: -0.1700
Data Index: 196785 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5368. Min Range: -7.5368
Max Act: 7.0993. Min Act: -0.1700
Data Index: 7028449 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5368. Min Range: -7.5368
Max Act: 7.0681. Min Act: -0.1700
Data Index: 7013034 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5368. Min Range: -7.5368
Max Act: 7.0056. Min Act: -0.1700
Data Index: 5197386 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.9431. Min Act: -0.1700
Data Index: 6338400 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.9118. Min Act: -0.1700
Data Index: 8157993 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.9118. Min Act: -0.1700
Data Index: 5455000 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.9118. Min Act: -0.1700
Data Index: 5543812 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.9118. Min Act: -0.1700
Data Index: 6250321 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.9118. Min Act: -0.1700
Data Index: 2121771 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.9118. Min Act: -0.1700
Data Index: 7626284 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.8806. Min Act: -0.1700
Data Index: 420702 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.9118. Min Act: -0.1700
Data Index: 4174673 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.8806. Min Act: -0.1700
Data Index: 8188014 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.8806. Min Act: -0.1700
Data Index: 3142433 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.8806. Min Act: -0.1700
Data Index: 656668 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5368. Min Range: -7.5368
Max Act: 6.8806. Min Act: -0.1700
Data Index: 1040501 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19