Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5335 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.7707. Min Act: -0.1700
Data Index: 4867323 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.7707. Min Act: -0.1700
Data Index: 1905019 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.6457. Min Act: -0.1700
Data Index: 1084273 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.6457. Min Act: -0.1700
Data Index: 282445 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.6457. Min Act: -0.1700
Data Index: 752719 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.5207. Min Act: -0.1700
Data Index: 5438756 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.5832. Min Act: -0.1700
Data Index: 6540442 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.5832. Min Act: -0.1700
Data Index: 7484632 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.5207. Min Act: -0.1700
Data Index: 4233490 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.5207. Min Act: -0.1700
Data Index: 3396293 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.4582. Min Act: -0.1700
Data Index: 8810275 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.4582. Min Act: -0.1700
Data Index: 6352881 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.5207. Min Act: -0.1700
Data Index: 5554788 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.4582. Min Act: -0.1700
Data Index: 4037103 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.4582. Min Act: -0.1700
Data Index: 3632982 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.4582. Min Act: -0.1700
Data Index: 5446125 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.4582. Min Act: -0.1700
Data Index: 508710 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.4582. Min Act: -0.1700
Data Index: 4650650 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.3957. Min Act: -0.1700
Data Index: 6223276 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7707. Min Range: -8.7707
Max Act: 8.3957. Min Act: -0.1700
Data Index: 5319597 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19