Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0926. Min Range: -6.0926
Max Act: 6.0926. Min Act: -0.1700
Data Index: 2767910 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.4676. Min Act: -0.1700
Data Index: 774218 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.4363. Min Act: -0.1700
Data Index: 5361748 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.4363. Min Act: -0.1700
Data Index: 5229715 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.4363. Min Act: -0.1700
Data Index: 3174503 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.4051. Min Act: -0.1700
Data Index: 452347 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.3738. Min Act: -0.1700
Data Index: 6901982 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.2801. Min Act: -0.1700
Data Index: 4603806 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.3426. Min Act: -0.1700
Data Index: 942247 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.3113. Min Act: -0.1700
Data Index: 1947095 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.2176. Min Act: -0.1700
Data Index: 8563654 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.2176. Min Act: -0.1700
Data Index: 6415070 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.2176. Min Act: -0.1700
Data Index: 867351 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.1863. Min Act: -0.1700
Data Index: 438236 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.1863. Min Act: -0.1700
Data Index: 3945032 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.1551. Min Act: -0.1700
Data Index: 3108285 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.1551. Min Act: -0.1700
Data Index: 4079568 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.1551. Min Act: -0.1700
Data Index: 7433147 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.0926. Min Act: -0.1700
Data Index: 7876764 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0926. Min Range: -6.0926
Max Act: 5.0926. Min Act: -0.1700
Data Index: 5826157 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19